{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:5VL3OL64UGP6J3YULPO7AJIFLR","short_pith_number":"pith:5VL3OL64","canonical_record":{"source":{"id":"2212.08860","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-17T12:45:08Z","cross_cats_sorted":[],"title_canon_sha256":"d159322962ada6be8b8fb022569ecd31b13ab603c871bcc9ce8a14578238e01f","abstract_canon_sha256":"7cf3399fddf87ebe140b00d3bd1a5ac16739f961912d5759d0d9d4783fe97e54"},"schema_version":"1.0"},"canonical_sha256":"ed57b72fdca19fe4ef145bddf025055c5be9c615c16d743ceafc56744dd5d161","source":{"kind":"arxiv","id":"2212.08860","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08860","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08860v1","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08860","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"pith_short_12","alias_value":"5VL3OL64UGP6","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"pith_short_16","alias_value":"5VL3OL64UGP6J3YU","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"pith_short_8","alias_value":"5VL3OL64","created_at":"2026-07-05T05:26:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:5VL3OL64UGP6J3YULPO7AJIFLR","target":"record","payload":{"canonical_record":{"source":{"id":"2212.08860","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-17T12:45:08Z","cross_cats_sorted":[],"title_canon_sha256":"d159322962ada6be8b8fb022569ecd31b13ab603c871bcc9ce8a14578238e01f","abstract_canon_sha256":"7cf3399fddf87ebe140b00d3bd1a5ac16739f961912d5759d0d9d4783fe97e54"},"schema_version":"1.0"},"canonical_sha256":"ed57b72fdca19fe4ef145bddf025055c5be9c615c16d743ceafc56744dd5d161","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:15.060250Z","signature_b64":"c8LUKFWGncGasxf5djVYEuo4L80m4Qqp/cL4wIO/hl0/exgpIcDgF+8fSQdbJ/gayMGHNWj9PHH96HBIFabuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed57b72fdca19fe4ef145bddf025055c5be9c615c16d743ceafc56744dd5d161","last_reissued_at":"2026-07-05T05:26:15.059903Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:15.059903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.08860","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":"2026-07-05T05:26:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CjDPx8tsxJqVgIglYkDOQbm9CLuDYlDHYxA/ZdfHoZqjS1BFXX9Tdp0BS1CJVjH4Ptm1kn81hFV2PdHqKBVWDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:17:37.278290Z"},"content_sha256":"1af05ebc94fd1adfbaa2fcfa2320f12970a9f57bfb1e6baa1fca363220fbf006","schema_version":"1.0","event_id":"sha256:1af05ebc94fd1adfbaa2fcfa2320f12970a9f57bfb1e6baa1fca363220fbf006"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:5VL3OL64UGP6J3YULPO7AJIFLR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Yuan, Huazhe Xu, Xueqian Wang, Yang Gao, Yi Wu, Zhecheng Yuan, Zhengrong Xue","submitted_at":"2022-12-17T12:45:08Z","abstract_excerpt":"Learning generalizable policies that can adapt to unseen environments remains challenging in visual Reinforcement Learning (RL). Existing approaches try to acquire a robust representation via diversifying the appearances of in-domain observations for better generalization. Limited by the specific observations of the environment, these methods ignore the possibility of exploring diverse real-world image datasets. In this paper, we investigate how a visual RL agent would benefit from the off-the-shelf visual representations. Surprisingly, we find that the early layers in an ImageNet pre-trained "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08860","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/2212.08860/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":"2026-07-05T05:26:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7vVravUlunXJjRnC1ZoUypIU0Sy/KLrlXAUnxpliGg8f3qPh+ye1MGsRW8oyOiEcMtpDwBE9p3L1AgFtroSdBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:17:37.278785Z"},"content_sha256":"ffc20c8b63877d29e7f87eb2de9a0fc5dbfeedae65b8edb718f65681b093512d","schema_version":"1.0","event_id":"sha256:ffc20c8b63877d29e7f87eb2de9a0fc5dbfeedae65b8edb718f65681b093512d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5VL3OL64UGP6J3YULPO7AJIFLR/bundle.json","state_url":"https://pith.science/pith/5VL3OL64UGP6J3YULPO7AJIFLR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5VL3OL64UGP6J3YULPO7AJIFLR/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":"2026-08-09T21:17:37Z","links":{"resolver":"https://pith.science/pith/5VL3OL64UGP6J3YULPO7AJIFLR","bundle":"https://pith.science/pith/5VL3OL64UGP6J3YULPO7AJIFLR/bundle.json","state":"https://pith.science/pith/5VL3OL64UGP6J3YULPO7AJIFLR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5VL3OL64UGP6J3YULPO7AJIFLR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5VL3OL64UGP6J3YULPO7AJIFLR","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":"7cf3399fddf87ebe140b00d3bd1a5ac16739f961912d5759d0d9d4783fe97e54","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-17T12:45:08Z","title_canon_sha256":"d159322962ada6be8b8fb022569ecd31b13ab603c871bcc9ce8a14578238e01f"},"schema_version":"1.0","source":{"id":"2212.08860","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08860","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08860v1","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08860","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"pith_short_12","alias_value":"5VL3OL64UGP6","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"pith_short_16","alias_value":"5VL3OL64UGP6J3YU","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"pith_short_8","alias_value":"5VL3OL64","created_at":"2026-07-05T05:26:15Z"}],"graph_snapshots":[{"event_id":"sha256:ffc20c8b63877d29e7f87eb2de9a0fc5dbfeedae65b8edb718f65681b093512d","target":"graph","created_at":"2026-07-05T05:26:15Z","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/2212.08860/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning generalizable policies that can adapt to unseen environments remains challenging in visual Reinforcement Learning (RL). Existing approaches try to acquire a robust representation via diversifying the appearances of in-domain observations for better generalization. Limited by the specific observations of the environment, these methods ignore the possibility of exploring diverse real-world image datasets. In this paper, we investigate how a visual RL agent would benefit from the off-the-shelf visual representations. Surprisingly, we find that the early layers in an ImageNet pre-trained ","authors_text":"Bo Yuan, Huazhe Xu, Xueqian Wang, Yang Gao, Yi Wu, Zhecheng Yuan, Zhengrong Xue","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-17T12:45:08Z","title":"Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08860","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":"sha256:1af05ebc94fd1adfbaa2fcfa2320f12970a9f57bfb1e6baa1fca363220fbf006","target":"record","created_at":"2026-07-05T05:26:15Z","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":"7cf3399fddf87ebe140b00d3bd1a5ac16739f961912d5759d0d9d4783fe97e54","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-17T12:45:08Z","title_canon_sha256":"d159322962ada6be8b8fb022569ecd31b13ab603c871bcc9ce8a14578238e01f"},"schema_version":"1.0","source":{"id":"2212.08860","kind":"arxiv","version":1}},"canonical_sha256":"ed57b72fdca19fe4ef145bddf025055c5be9c615c16d743ceafc56744dd5d161","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed57b72fdca19fe4ef145bddf025055c5be9c615c16d743ceafc56744dd5d161","first_computed_at":"2026-07-05T05:26:15.059903Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:26:15.059903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c8LUKFWGncGasxf5djVYEuo4L80m4Qqp/cL4wIO/hl0/exgpIcDgF+8fSQdbJ/gayMGHNWj9PHH96HBIFabuAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:26:15.060250Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.08860","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1af05ebc94fd1adfbaa2fcfa2320f12970a9f57bfb1e6baa1fca363220fbf006","sha256:ffc20c8b63877d29e7f87eb2de9a0fc5dbfeedae65b8edb718f65681b093512d"],"state_sha256":"70c7d21bb1c6725144b4c557d1b3a5241c737dcf775699ba53882bed9e5a879a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w7n7QdVrrRhJ/kNSRN6G/HkalNcmD87y37MblUkom6di6Ow+WP8Nz8fsrRPkMJrwYph3eIlPia5rwmU1bBJ0BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T21:17:37.282725Z","bundle_sha256":"a4d685d09d14c44672fe420ebc98628200dcf81fdf865e25d72fb400b2315812"}}