{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ESQBSUNHQBCG7RMVKY6BLQB2VZ","short_pith_number":"pith:ESQBSUNH","canonical_record":{"source":{"id":"2311.02227","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T20:32:30Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"8cb8d4d7f9b92ae5f6aebb77db70684568ca721473607eeee794038ed747c4f5","abstract_canon_sha256":"51d5bc03c8b41ef1063f78ca46d46c8a725c4041dd3ad6045bb7c4f71dd67b4c"},"schema_version":"1.0"},"canonical_sha256":"24a01951a780446fc595563c15c03aae6749f29223ab1ee7a569326c311dd361","source":{"kind":"arxiv","id":"2311.02227","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.02227","created_at":"2026-07-05T07:22:50Z"},{"alias_kind":"arxiv_version","alias_value":"2311.02227v2","created_at":"2026-07-05T07:22:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02227","created_at":"2026-07-05T07:22:50Z"},{"alias_kind":"pith_short_12","alias_value":"ESQBSUNHQBCG","created_at":"2026-07-05T07:22:50Z"},{"alias_kind":"pith_short_16","alias_value":"ESQBSUNHQBCG7RMV","created_at":"2026-07-05T07:22:50Z"},{"alias_kind":"pith_short_8","alias_value":"ESQBSUNH","created_at":"2026-07-05T07:22:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ESQBSUNHQBCG7RMVKY6BLQB2VZ","target":"record","payload":{"canonical_record":{"source":{"id":"2311.02227","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T20:32:30Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"8cb8d4d7f9b92ae5f6aebb77db70684568ca721473607eeee794038ed747c4f5","abstract_canon_sha256":"51d5bc03c8b41ef1063f78ca46d46c8a725c4041dd3ad6045bb7c4f71dd67b4c"},"schema_version":"1.0"},"canonical_sha256":"24a01951a780446fc595563c15c03aae6749f29223ab1ee7a569326c311dd361","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:50.614133Z","signature_b64":"Km9gmpsG2Td21T66lMKDmLqPN7Ry6uAEkR3euLhfRHW8gRVyvv5UkJ8pZefLA0hgDFJgOsAJwmtbsmP8Dc1ZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24a01951a780446fc595563c15c03aae6749f29223ab1ee7a569326c311dd361","last_reissued_at":"2026-07-05T07:22:50.613668Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:50.613668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.02227","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:22:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U/oMsn51B4G0lJDIA0LsyLosm+1gBk4NbRWkHfa7cHaDYSviqVvWgmIKGuAqdz2WCTmIZy2iOuKXADiQGH0uBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:30:05.178565Z"},"content_sha256":"5ec73503dd0211a3083e94e94241985e6604f14a42de9c0524db155af16d77f4","schema_version":"1.0","event_id":"sha256:5ec73503dd0211a3083e94e94241985e6604f14a42de9c0524db155af16d77f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ESQBSUNHQBCG7RMVKY6BLQB2VZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"State-Wise Safe Reinforcement Learning With Pixel Observations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Chao Huang, Qingyuan Wu, Qi Zhu, Ruochen Jiao, Simon Sinong Zhan, Yixuan Wang","submitted_at":"2023-11-03T20:32:30Z","abstract_excerpt":"In the context of safe exploration, Reinforcement Learning (RL) has long grappled with the challenges of balancing the tradeoff between maximizing rewards and minimizing safety violations, particularly in complex environments with contact-rich or non-smooth dynamics, and when dealing with high-dimensional pixel observations. Furthermore, incorporating state-wise safety constraints in the exploration and learning process, where the agent must avoid unsafe regions without prior knowledge, adds another layer of complexity. In this paper, we propose a novel pixel-observation safe RL algorithm that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02227","kind":"arxiv","version":2},"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/2311.02227/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":"2026-07-05T07:22:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SUUG4qL3O+uiGSSRkCuUv0DtcC6E+XYHJSJ8SN+eAjQlqd/aq8FiWeK8fzma/876vmyg9GLNItRQEhVjEDWmDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:30:05.179125Z"},"content_sha256":"c50eec51cb8268ae4ba901a6b857ad335603af82e54543bbd8863539a0fb86e2","schema_version":"1.0","event_id":"sha256:c50eec51cb8268ae4ba901a6b857ad335603af82e54543bbd8863539a0fb86e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ESQBSUNHQBCG7RMVKY6BLQB2VZ/bundle.json","state_url":"https://pith.science/pith/ESQBSUNHQBCG7RMVKY6BLQB2VZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ESQBSUNHQBCG7RMVKY6BLQB2VZ/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":"2026-07-06T23:30:05Z","links":{"resolver":"https://pith.science/pith/ESQBSUNHQBCG7RMVKY6BLQB2VZ","bundle":"https://pith.science/pith/ESQBSUNHQBCG7RMVKY6BLQB2VZ/bundle.json","state":"https://pith.science/pith/ESQBSUNHQBCG7RMVKY6BLQB2VZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ESQBSUNHQBCG7RMVKY6BLQB2VZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ESQBSUNHQBCG7RMVKY6BLQB2VZ","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":"51d5bc03c8b41ef1063f78ca46d46c8a725c4041dd3ad6045bb7c4f71dd67b4c","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T20:32:30Z","title_canon_sha256":"8cb8d4d7f9b92ae5f6aebb77db70684568ca721473607eeee794038ed747c4f5"},"schema_version":"1.0","source":{"id":"2311.02227","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.02227","created_at":"2026-07-05T07:22:50Z"},{"alias_kind":"arxiv_version","alias_value":"2311.02227v2","created_at":"2026-07-05T07:22:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02227","created_at":"2026-07-05T07:22:50Z"},{"alias_kind":"pith_short_12","alias_value":"ESQBSUNHQBCG","created_at":"2026-07-05T07:22:50Z"},{"alias_kind":"pith_short_16","alias_value":"ESQBSUNHQBCG7RMV","created_at":"2026-07-05T07:22:50Z"},{"alias_kind":"pith_short_8","alias_value":"ESQBSUNH","created_at":"2026-07-05T07:22:50Z"}],"graph_snapshots":[{"event_id":"sha256:c50eec51cb8268ae4ba901a6b857ad335603af82e54543bbd8863539a0fb86e2","target":"graph","created_at":"2026-07-05T07:22:50Z","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/2311.02227/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the context of safe exploration, Reinforcement Learning (RL) has long grappled with the challenges of balancing the tradeoff between maximizing rewards and minimizing safety violations, particularly in complex environments with contact-rich or non-smooth dynamics, and when dealing with high-dimensional pixel observations. Furthermore, incorporating state-wise safety constraints in the exploration and learning process, where the agent must avoid unsafe regions without prior knowledge, adds another layer of complexity. In this paper, we propose a novel pixel-observation safe RL algorithm that","authors_text":"Chao Huang, Qingyuan Wu, Qi Zhu, Ruochen Jiao, Simon Sinong Zhan, Yixuan Wang","cross_cats":["cs.AI","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T20:32:30Z","title":"State-Wise Safe Reinforcement Learning With Pixel Observations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02227","kind":"arxiv","version":2},"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":"sha256:5ec73503dd0211a3083e94e94241985e6604f14a42de9c0524db155af16d77f4","target":"record","created_at":"2026-07-05T07:22:50Z","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":"51d5bc03c8b41ef1063f78ca46d46c8a725c4041dd3ad6045bb7c4f71dd67b4c","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T20:32:30Z","title_canon_sha256":"8cb8d4d7f9b92ae5f6aebb77db70684568ca721473607eeee794038ed747c4f5"},"schema_version":"1.0","source":{"id":"2311.02227","kind":"arxiv","version":2}},"canonical_sha256":"24a01951a780446fc595563c15c03aae6749f29223ab1ee7a569326c311dd361","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24a01951a780446fc595563c15c03aae6749f29223ab1ee7a569326c311dd361","first_computed_at":"2026-07-05T07:22:50.613668Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:22:50.613668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Km9gmpsG2Td21T66lMKDmLqPN7Ry6uAEkR3euLhfRHW8gRVyvv5UkJ8pZefLA0hgDFJgOsAJwmtbsmP8Dc1ZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:22:50.614133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.02227","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ec73503dd0211a3083e94e94241985e6604f14a42de9c0524db155af16d77f4","sha256:c50eec51cb8268ae4ba901a6b857ad335603af82e54543bbd8863539a0fb86e2"],"state_sha256":"c7e494aa87289c078d565f2e0cb6c001b3e1ed0d39b044cec167935576193135"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KzwqAuPRZxCPkQISHj6cbsAJyYDcA20JlyM5sjIbquAqRdn0TV74gzN3QkyuVMpDrxiyWNWZhiOVhY7Q3rLCCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:30:05.181148Z","bundle_sha256":"7d1f069b683350c59e8503260f0070c08ef3870d41d007f6f68c605645380f1f"}}