{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MW64X7SSOBIRZBR3EA5DQMUQSH","short_pith_number":"pith:MW64X7SS","canonical_record":{"source":{"id":"2402.09838","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T10:00:13Z","cross_cats_sorted":[],"title_canon_sha256":"fc71aa3316b1bf28874419c0aa90785f24bca0f9bdfd41d5ff7a94332201e35c","abstract_canon_sha256":"f9c7ee36fb3e4006c40c7cf9e7afb5901842e75641bee21e58001d8a889cf534"},"schema_version":"1.0"},"canonical_sha256":"65bdcbfe5270511c863b203a38329091f8daeb5ca149f538ec47e0f9527bf103","source":{"kind":"arxiv","id":"2402.09838","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09838","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09838v2","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09838","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"pith_short_12","alias_value":"MW64X7SSOBIR","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"pith_short_16","alias_value":"MW64X7SSOBIRZBR3","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"pith_short_8","alias_value":"MW64X7SS","created_at":"2026-07-05T08:25:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MW64X7SSOBIRZBR3EA5DQMUQSH","target":"record","payload":{"canonical_record":{"source":{"id":"2402.09838","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T10:00:13Z","cross_cats_sorted":[],"title_canon_sha256":"fc71aa3316b1bf28874419c0aa90785f24bca0f9bdfd41d5ff7a94332201e35c","abstract_canon_sha256":"f9c7ee36fb3e4006c40c7cf9e7afb5901842e75641bee21e58001d8a889cf534"},"schema_version":"1.0"},"canonical_sha256":"65bdcbfe5270511c863b203a38329091f8daeb5ca149f538ec47e0f9527bf103","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:31.984724Z","signature_b64":"WNtCUHSu7ddFrbD0Sx2QU25W+OWz6zXWzmcUl1u1NBwqRDolNgWzGf/bmSmKVtABIdJ0W+I5ZgqW04e58fcoCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65bdcbfe5270511c863b203a38329091f8daeb5ca149f538ec47e0f9527bf103","last_reissued_at":"2026-07-05T08:25:31.984278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:31.984278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.09838","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":"2026-07-05T08:25:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WueYc0sC1rUJlMe4H30Xv+zjvEIpAnrxAhJYnpzQeanTxd4gUVgW96f1PZpI8msG/JxYLpZljZaTyHk1iQX4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:45:25.261900Z"},"content_sha256":"5b9c969e0dd2f238f50930f7bb903cb6df73da8ecb813188f81e7849b825c50c","schema_version":"1.0","event_id":"sha256:5b9c969e0dd2f238f50930f7bb903cb6df73da8ecb813188f81e7849b825c50c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MW64X7SSOBIRZBR3EA5DQMUQSH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Performative Reinforcement Learning in Gradually Shifting Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ben Rank, Debmalya Mandal, Goran Radanovic, Stelios Triantafyllou","submitted_at":"2024-02-15T10:00:13Z","abstract_excerpt":"When Reinforcement Learning (RL) agents are deployed in practice, they might impact their environment and change its dynamics. We propose a new framework to model this phenomenon, where the current environment depends on the deployed policy as well as its previous dynamics. This is a generalization of Performative RL (PRL) [Mandal et al., 2023]. Unlike PRL, our framework allows to model scenarios where the environment gradually adjusts to a deployed policy. We adapt two algorithms from the performative prediction literature to our setting and propose a novel algorithm called Mixed Delayed Repe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09838","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/2402.09838/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":"2026-07-05T08:25:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OSH8TYkOWHNblBkacG9S4MtkC3c13GB+yJSoonqgflyeOGXd7CnC28t9j5L3ppWqqDWCAtX6QmijQChhzo/8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:45:25.262804Z"},"content_sha256":"7b8aac5c23cfd6f5bbce1bab630ee20996eaea648388e8885cf11c66e32e4a7a","schema_version":"1.0","event_id":"sha256:7b8aac5c23cfd6f5bbce1bab630ee20996eaea648388e8885cf11c66e32e4a7a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MW64X7SSOBIRZBR3EA5DQMUQSH/bundle.json","state_url":"https://pith.science/pith/MW64X7SSOBIRZBR3EA5DQMUQSH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MW64X7SSOBIRZBR3EA5DQMUQSH/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":"2026-08-10T17:45:25Z","links":{"resolver":"https://pith.science/pith/MW64X7SSOBIRZBR3EA5DQMUQSH","bundle":"https://pith.science/pith/MW64X7SSOBIRZBR3EA5DQMUQSH/bundle.json","state":"https://pith.science/pith/MW64X7SSOBIRZBR3EA5DQMUQSH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MW64X7SSOBIRZBR3EA5DQMUQSH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MW64X7SSOBIRZBR3EA5DQMUQSH","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":"f9c7ee36fb3e4006c40c7cf9e7afb5901842e75641bee21e58001d8a889cf534","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T10:00:13Z","title_canon_sha256":"fc71aa3316b1bf28874419c0aa90785f24bca0f9bdfd41d5ff7a94332201e35c"},"schema_version":"1.0","source":{"id":"2402.09838","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09838","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09838v2","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09838","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"pith_short_12","alias_value":"MW64X7SSOBIR","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"pith_short_16","alias_value":"MW64X7SSOBIRZBR3","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"pith_short_8","alias_value":"MW64X7SS","created_at":"2026-07-05T08:25:31Z"}],"graph_snapshots":[{"event_id":"sha256:7b8aac5c23cfd6f5bbce1bab630ee20996eaea648388e8885cf11c66e32e4a7a","target":"graph","created_at":"2026-07-05T08:25:31Z","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/2402.09838/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When Reinforcement Learning (RL) agents are deployed in practice, they might impact their environment and change its dynamics. We propose a new framework to model this phenomenon, where the current environment depends on the deployed policy as well as its previous dynamics. This is a generalization of Performative RL (PRL) [Mandal et al., 2023]. Unlike PRL, our framework allows to model scenarios where the environment gradually adjusts to a deployed policy. We adapt two algorithms from the performative prediction literature to our setting and propose a novel algorithm called Mixed Delayed Repe","authors_text":"Ben Rank, Debmalya Mandal, Goran Radanovic, Stelios Triantafyllou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T10:00:13Z","title":"Performative Reinforcement Learning in Gradually Shifting Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09838","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":"sha256:5b9c969e0dd2f238f50930f7bb903cb6df73da8ecb813188f81e7849b825c50c","target":"record","created_at":"2026-07-05T08:25:31Z","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":"f9c7ee36fb3e4006c40c7cf9e7afb5901842e75641bee21e58001d8a889cf534","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T10:00:13Z","title_canon_sha256":"fc71aa3316b1bf28874419c0aa90785f24bca0f9bdfd41d5ff7a94332201e35c"},"schema_version":"1.0","source":{"id":"2402.09838","kind":"arxiv","version":2}},"canonical_sha256":"65bdcbfe5270511c863b203a38329091f8daeb5ca149f538ec47e0f9527bf103","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65bdcbfe5270511c863b203a38329091f8daeb5ca149f538ec47e0f9527bf103","first_computed_at":"2026-07-05T08:25:31.984278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:31.984278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WNtCUHSu7ddFrbD0Sx2QU25W+OWz6zXWzmcUl1u1NBwqRDolNgWzGf/bmSmKVtABIdJ0W+I5ZgqW04e58fcoCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:31.984724Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.09838","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b9c969e0dd2f238f50930f7bb903cb6df73da8ecb813188f81e7849b825c50c","sha256:7b8aac5c23cfd6f5bbce1bab630ee20996eaea648388e8885cf11c66e32e4a7a"],"state_sha256":"be981b18cc85e9709c62f04be351d5aa169b5c0d9a35c8a52913d65fbaec9252"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yh/eLCL5VH9nKce47Bq6VyuTrhA8CF6z/fDhqwuyKg9grU9RZv+lodFi/ybsDLuIgZp87Pu88MBF8gvQzAHqBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T17:45:25.268267Z","bundle_sha256":"5662a70fa11c52b0a6bdd1c181195d0022e98e24d1a4d4bc3f858f25f186e1cf"}}