{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ECY4AFVACQBC2JN5FFIUPYZVVK","short_pith_number":"pith:ECY4AFVA","canonical_record":{"source":{"id":"2502.09923","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-14T05:23:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f6a55470c5f4802fa0093a866e4410391106ad27f9f020c80dfc389fe91dff43","abstract_canon_sha256":"86c72465242bb68da41d92066662a220a334f609c62419576308278d15651edd"},"schema_version":"1.0"},"canonical_sha256":"20b1c016a014022d25bd295147e335aa9498707a716dff7da35c122bc961a3d9","source":{"kind":"arxiv","id":"2502.09923","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09923","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09923v1","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09923","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"pith_short_12","alias_value":"ECY4AFVACQBC","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"pith_short_16","alias_value":"ECY4AFVACQBC2JN5","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"pith_short_8","alias_value":"ECY4AFVA","created_at":"2026-07-05T10:14:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ECY4AFVACQBC2JN5FFIUPYZVVK","target":"record","payload":{"canonical_record":{"source":{"id":"2502.09923","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-14T05:23:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f6a55470c5f4802fa0093a866e4410391106ad27f9f020c80dfc389fe91dff43","abstract_canon_sha256":"86c72465242bb68da41d92066662a220a334f609c62419576308278d15651edd"},"schema_version":"1.0"},"canonical_sha256":"20b1c016a014022d25bd295147e335aa9498707a716dff7da35c122bc961a3d9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:14.388856Z","signature_b64":"m6SWmku8PlqbHK0qM/DrVSaYwCWP5XMNR6RKglz224iK+8Dhf0QZwQIhtOE44pZ7bPB4P0JGwuOoj+J+e9VVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20b1c016a014022d25bd295147e335aa9498707a716dff7da35c122bc961a3d9","last_reissued_at":"2026-07-05T10:14:14.388379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:14.388379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.09923","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":"2026-07-05T10:14:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wb/OJ+HO6saAoBCrnk4DOVau6kitgciqXuSOTFBdsQYkaUYR6Gvx0KCtnX9vwK2VjSva87lBNu4RsXicKFTTDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:08:55.104037Z"},"content_sha256":"7c104f15d99f2ebd481dba8568912760ec1bd46d895241907d35775b9536a644","schema_version":"1.0","event_id":"sha256:7c104f15d99f2ebd481dba8568912760ec1bd46d895241907d35775b9536a644"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ECY4AFVACQBC2JN5FFIUPYZVVK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Consistent Model-based Adaptation for Visual Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chengyang Ying, Hang Su, Jun Zhu, Xinning Zhou, Yao Feng","submitted_at":"2025-02-14T05:23:56Z","abstract_excerpt":"Visual reinforcement learning agents typically face serious performance declines in real-world applications caused by visual distractions. Existing methods rely on fine-tuning the policy's representations with hand-crafted augmentations. In this work, we propose Self-Consistent Model-based Adaptation (SCMA), a novel method that fosters robust adaptation without modifying the policy. By transferring cluttered observations to clean ones with a denoising model, SCMA can mitigate distractions for various policies as a plug-and-play enhancement. To optimize the denoising model in an unsupervised ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09923","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/2502.09923/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":"2026-07-05T10:14:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"THgtjZXlrFsJ3dCuFClghuKOf/r2jpRi4ZQkqzVH/KzG+X0z/3MSx3JDopfHpDxlYRSSXMK2c7HeWUzKPI7MBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:08:55.104592Z"},"content_sha256":"8c8c401e9a842d53baaf12a642b79977f2d9a76cd24286773f530b06a8c7aca4","schema_version":"1.0","event_id":"sha256:8c8c401e9a842d53baaf12a642b79977f2d9a76cd24286773f530b06a8c7aca4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ECY4AFVACQBC2JN5FFIUPYZVVK/bundle.json","state_url":"https://pith.science/pith/ECY4AFVACQBC2JN5FFIUPYZVVK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ECY4AFVACQBC2JN5FFIUPYZVVK/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":"2026-08-08T04:08:55Z","links":{"resolver":"https://pith.science/pith/ECY4AFVACQBC2JN5FFIUPYZVVK","bundle":"https://pith.science/pith/ECY4AFVACQBC2JN5FFIUPYZVVK/bundle.json","state":"https://pith.science/pith/ECY4AFVACQBC2JN5FFIUPYZVVK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ECY4AFVACQBC2JN5FFIUPYZVVK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ECY4AFVACQBC2JN5FFIUPYZVVK","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":"86c72465242bb68da41d92066662a220a334f609c62419576308278d15651edd","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-14T05:23:56Z","title_canon_sha256":"f6a55470c5f4802fa0093a866e4410391106ad27f9f020c80dfc389fe91dff43"},"schema_version":"1.0","source":{"id":"2502.09923","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09923","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09923v1","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09923","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"pith_short_12","alias_value":"ECY4AFVACQBC","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"pith_short_16","alias_value":"ECY4AFVACQBC2JN5","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"pith_short_8","alias_value":"ECY4AFVA","created_at":"2026-07-05T10:14:14Z"}],"graph_snapshots":[{"event_id":"sha256:8c8c401e9a842d53baaf12a642b79977f2d9a76cd24286773f530b06a8c7aca4","target":"graph","created_at":"2026-07-05T10:14:14Z","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/2502.09923/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual reinforcement learning agents typically face serious performance declines in real-world applications caused by visual distractions. Existing methods rely on fine-tuning the policy's representations with hand-crafted augmentations. In this work, we propose Self-Consistent Model-based Adaptation (SCMA), a novel method that fosters robust adaptation without modifying the policy. By transferring cluttered observations to clean ones with a denoising model, SCMA can mitigate distractions for various policies as a plug-and-play enhancement. To optimize the denoising model in an unsupervised ma","authors_text":"Chengyang Ying, Hang Su, Jun Zhu, Xinning Zhou, Yao Feng","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-14T05:23:56Z","title":"Self-Consistent Model-based Adaptation for Visual Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09923","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":"sha256:7c104f15d99f2ebd481dba8568912760ec1bd46d895241907d35775b9536a644","target":"record","created_at":"2026-07-05T10:14:14Z","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":"86c72465242bb68da41d92066662a220a334f609c62419576308278d15651edd","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-14T05:23:56Z","title_canon_sha256":"f6a55470c5f4802fa0093a866e4410391106ad27f9f020c80dfc389fe91dff43"},"schema_version":"1.0","source":{"id":"2502.09923","kind":"arxiv","version":1}},"canonical_sha256":"20b1c016a014022d25bd295147e335aa9498707a716dff7da35c122bc961a3d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20b1c016a014022d25bd295147e335aa9498707a716dff7da35c122bc961a3d9","first_computed_at":"2026-07-05T10:14:14.388379Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:14.388379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m6SWmku8PlqbHK0qM/DrVSaYwCWP5XMNR6RKglz224iK+8Dhf0QZwQIhtOE44pZ7bPB4P0JGwuOoj+J+e9VVBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:14.388856Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.09923","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c104f15d99f2ebd481dba8568912760ec1bd46d895241907d35775b9536a644","sha256:8c8c401e9a842d53baaf12a642b79977f2d9a76cd24286773f530b06a8c7aca4"],"state_sha256":"4fc892e491e8461f39fd8b58c165b485a201e53d4dfb8e725899058a0ee18962"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0lTHByMUREb9NV83TgsXGVmpzxmOQVljLo4NSih84T5em0viGgrXRlKSEHm4YAN0GRhLUOWRVybPMtJ4/nVXAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:08:55.108286Z","bundle_sha256":"4cbab9bf2814589288bfecc046395eda6f4624340b27fe40f0a5090534e53f14"}}