{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2NNCC5O4HA2VHJNC2FHN3APWN6","short_pith_number":"pith:2NNCC5O4","canonical_record":{"source":{"id":"2405.11718","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-20T01:37:21Z","cross_cats_sorted":[],"title_canon_sha256":"4f1ac29db7efc37a79b8e64dfe2de493c371b406e60ca952e4205a4d821e846e","abstract_canon_sha256":"cf96c34dcf8acac22262a773cf963375d6627d8bee3fbf1c8a2f8ee5c19e0f43"},"schema_version":"1.0"},"canonical_sha256":"d35a2175dc383553a5a2d14edd81f66f840ea70268ea0a26e939a92265df7845","source":{"kind":"arxiv","id":"2405.11718","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11718","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11718v2","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11718","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"pith_short_12","alias_value":"2NNCC5O4HA2V","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"2NNCC5O4HA2VHJNC","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"2NNCC5O4","created_at":"2026-07-05T08:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2NNCC5O4HA2VHJNC2FHN3APWN6","target":"record","payload":{"canonical_record":{"source":{"id":"2405.11718","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-20T01:37:21Z","cross_cats_sorted":[],"title_canon_sha256":"4f1ac29db7efc37a79b8e64dfe2de493c371b406e60ca952e4205a4d821e846e","abstract_canon_sha256":"cf96c34dcf8acac22262a773cf963375d6627d8bee3fbf1c8a2f8ee5c19e0f43"},"schema_version":"1.0"},"canonical_sha256":"d35a2175dc383553a5a2d14edd81f66f840ea70268ea0a26e939a92265df7845","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:15.559220Z","signature_b64":"S5+R7bvb8opUHFVbOfUwWBH9CuPIJzh5PKs18eXS6zluEWcxe+kF2DHIKIEh45bmrYdXm94rea1GMUnI8O0ACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d35a2175dc383553a5a2d14edd81f66f840ea70268ea0a26e939a92265df7845","last_reissued_at":"2026-07-05T08:31:15.558813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:15.558813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.11718","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":"2026-07-05T08:31:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pFYTg2+rKA695ss/K7PZ71odxdntXHEnijEUNvMVZuZSUfVuGkY4aN1g1dLN29KdL6cFq+IHSeG5sQ3Kf1M8Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T19:48:24.750283Z"},"content_sha256":"486dbc3e04e09ad5f226bb5055f5e656383b42fa375251704d5c242019b5b467","schema_version":"1.0","event_id":"sha256:486dbc3e04e09ad5f226bb5055f5e656383b42fa375251704d5c242019b5b467"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2NNCC5O4HA2VHJNC2FHN3APWN6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Feasibility Consistent Representation Learning for Safe Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ding Zhao, Yihang Yao, Zhepeng Cen, Zuxin Liu","submitted_at":"2024-05-20T01:37:21Z","abstract_excerpt":"In the field of safe reinforcement learning (RL), finding a balance between satisfying safety constraints and optimizing reward performance presents a significant challenge. A key obstacle in this endeavor is the estimation of safety constraints, which is typically more difficult than estimating a reward metric due to the sparse nature of the constraint signals. To address this issue, we introduce a novel framework named Feasibility Consistent Safe Reinforcement Learning (FCSRL). This framework combines representation learning with feasibility-oriented objectives to identify and extract safety"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11718","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/2405.11718/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":"2026-07-05T08:31:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DArkMItxuVdtGLNjBrQyhTnMbN+6pzouQ40uMNVQIXmfW4iBdrAOOpBwHnJVhYMLQPqtlYiZVa1GpKYj9c6NCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T19:48:24.750984Z"},"content_sha256":"0dcef2a732c25a731da322e7c4bf8ec76dbc093fc9dbfe548d3365ad08237ecd","schema_version":"1.0","event_id":"sha256:0dcef2a732c25a731da322e7c4bf8ec76dbc093fc9dbfe548d3365ad08237ecd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2NNCC5O4HA2VHJNC2FHN3APWN6/bundle.json","state_url":"https://pith.science/pith/2NNCC5O4HA2VHJNC2FHN3APWN6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2NNCC5O4HA2VHJNC2FHN3APWN6/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":"2026-08-05T19:48:24Z","links":{"resolver":"https://pith.science/pith/2NNCC5O4HA2VHJNC2FHN3APWN6","bundle":"https://pith.science/pith/2NNCC5O4HA2VHJNC2FHN3APWN6/bundle.json","state":"https://pith.science/pith/2NNCC5O4HA2VHJNC2FHN3APWN6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2NNCC5O4HA2VHJNC2FHN3APWN6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2NNCC5O4HA2VHJNC2FHN3APWN6","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":"cf96c34dcf8acac22262a773cf963375d6627d8bee3fbf1c8a2f8ee5c19e0f43","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-20T01:37:21Z","title_canon_sha256":"4f1ac29db7efc37a79b8e64dfe2de493c371b406e60ca952e4205a4d821e846e"},"schema_version":"1.0","source":{"id":"2405.11718","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11718","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11718v2","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11718","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"pith_short_12","alias_value":"2NNCC5O4HA2V","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"2NNCC5O4HA2VHJNC","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"2NNCC5O4","created_at":"2026-07-05T08:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:0dcef2a732c25a731da322e7c4bf8ec76dbc093fc9dbfe548d3365ad08237ecd","target":"graph","created_at":"2026-07-05T08:31:15Z","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/2405.11718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the field of safe reinforcement learning (RL), finding a balance between satisfying safety constraints and optimizing reward performance presents a significant challenge. A key obstacle in this endeavor is the estimation of safety constraints, which is typically more difficult than estimating a reward metric due to the sparse nature of the constraint signals. To address this issue, we introduce a novel framework named Feasibility Consistent Safe Reinforcement Learning (FCSRL). This framework combines representation learning with feasibility-oriented objectives to identify and extract safety","authors_text":"Ding Zhao, Yihang Yao, Zhepeng Cen, Zuxin Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-20T01:37:21Z","title":"Feasibility Consistent Representation Learning for Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11718","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":"sha256:486dbc3e04e09ad5f226bb5055f5e656383b42fa375251704d5c242019b5b467","target":"record","created_at":"2026-07-05T08:31:15Z","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":"cf96c34dcf8acac22262a773cf963375d6627d8bee3fbf1c8a2f8ee5c19e0f43","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-20T01:37:21Z","title_canon_sha256":"4f1ac29db7efc37a79b8e64dfe2de493c371b406e60ca952e4205a4d821e846e"},"schema_version":"1.0","source":{"id":"2405.11718","kind":"arxiv","version":2}},"canonical_sha256":"d35a2175dc383553a5a2d14edd81f66f840ea70268ea0a26e939a92265df7845","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d35a2175dc383553a5a2d14edd81f66f840ea70268ea0a26e939a92265df7845","first_computed_at":"2026-07-05T08:31:15.558813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:15.558813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S5+R7bvb8opUHFVbOfUwWBH9CuPIJzh5PKs18eXS6zluEWcxe+kF2DHIKIEh45bmrYdXm94rea1GMUnI8O0ACg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:15.559220Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.11718","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:486dbc3e04e09ad5f226bb5055f5e656383b42fa375251704d5c242019b5b467","sha256:0dcef2a732c25a731da322e7c4bf8ec76dbc093fc9dbfe548d3365ad08237ecd"],"state_sha256":"cd22dbf15132ae490bd6e411a2d7f6ce2e1454cf2979fc773decddfea83e20be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GBoe+8j2qyop0bnmaCp24rGNT+32sFe9mTjKlGV3vy8tY6DStmTboGfc89tMxcUAc2JepWS19JmG87yT6Bh+CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T19:48:24.757495Z","bundle_sha256":"32f860a243c73b99aa5f92ccdf4f13fac1862576fdfa6c8d8fce2fb386504a76"}}