{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XD27MZ74LOODBVCMJDOHK63S33","short_pith_number":"pith:XD27MZ74","canonical_record":{"source":{"id":"2405.14114","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T02:41:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bc91669e851a9fd128e4844f4b1eb9e82c87c61a4a894112028c291114d6a602","abstract_canon_sha256":"30880fa73b09851d6ce3dd8d92b06b63ee602e021cc58256ec0e625e49320c37"},"schema_version":"1.0"},"canonical_sha256":"b8f5f667fc5b9c30d44c48dc757b72deed88ef3223cf1c15cd2b55eff588b59c","source":{"kind":"arxiv","id":"2405.14114","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14114","created_at":"2026-07-05T08:24:06Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14114v2","created_at":"2026-07-05T08:24:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14114","created_at":"2026-07-05T08:24:06Z"},{"alias_kind":"pith_short_12","alias_value":"XD27MZ74LOOD","created_at":"2026-07-05T08:24:06Z"},{"alias_kind":"pith_short_16","alias_value":"XD27MZ74LOODBVCM","created_at":"2026-07-05T08:24:06Z"},{"alias_kind":"pith_short_8","alias_value":"XD27MZ74","created_at":"2026-07-05T08:24:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XD27MZ74LOODBVCMJDOHK63S33","target":"record","payload":{"canonical_record":{"source":{"id":"2405.14114","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T02:41:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bc91669e851a9fd128e4844f4b1eb9e82c87c61a4a894112028c291114d6a602","abstract_canon_sha256":"30880fa73b09851d6ce3dd8d92b06b63ee602e021cc58256ec0e625e49320c37"},"schema_version":"1.0"},"canonical_sha256":"b8f5f667fc5b9c30d44c48dc757b72deed88ef3223cf1c15cd2b55eff588b59c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:06.173360Z","signature_b64":"2vPPTNYPzHmiYTXEA4DtxuozzqyRtrDKFYdsa8gOA08mz4kKmkz/hCqMId2PDHEoCMY/q+CY1ETXLMGXpFqGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8f5f667fc5b9c30d44c48dc757b72deed88ef3223cf1c15cd2b55eff588b59c","last_reissued_at":"2026-07-05T08:24:06.172820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:06.172820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.14114","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":"2026-07-05T08:24:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hDpuEe5HGhxdRvWaZXGwPKE4HgurW74s9u5Lv1FB2U5swZiUG+NHpL68gnFrKub5vfF9tRGYYnI9gtsjhdYRAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T11:45:04.652106Z"},"content_sha256":"a4f6230efae9ef385938405a421b839c0f2ed0d552bfe3cdf7118f7d6e0423fc","schema_version":"1.0","event_id":"sha256:a4f6230efae9ef385938405a421b839c0f2ed0d552bfe3cdf7118f7d6e0423fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XD27MZ74LOODBVCMJDOHK63S33","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Reinforcement Learning from Datasets with Structured Non-Stationarity","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Johannes Ackermann, Masashi Sugiyama, Takayuki Osa","submitted_at":"2024-05-23T02:41:36Z","abstract_excerpt":"Current Reinforcement Learning (RL) is often limited by the large amount of data needed to learn a successful policy. Offline RL aims to solve this issue by using transitions collected by a different behavior policy. We address a novel Offline RL problem setting in which, while collecting the dataset, the transition and reward functions gradually change between episodes but stay constant within each episode. We propose a method based on Contrastive Predictive Coding that identifies this non-stationarity in the offline dataset, accounts for it when training a policy, and predicts it during eval"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14114","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/2405.14114/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":"2026-07-05T08:24:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i72N4U36YJG98NmMd3fuEcxIfFFI26DYl9KDtfUea/2Reizek1XcNpb6n8tyKIOd7FnAwkwrqnuKKj8MD+u7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T11:45:04.652483Z"},"content_sha256":"40651c7d36509e26143af36da2df32f0a5dcf337c11253c88ed93d452a02a742","schema_version":"1.0","event_id":"sha256:40651c7d36509e26143af36da2df32f0a5dcf337c11253c88ed93d452a02a742"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XD27MZ74LOODBVCMJDOHK63S33/bundle.json","state_url":"https://pith.science/pith/XD27MZ74LOODBVCMJDOHK63S33/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XD27MZ74LOODBVCMJDOHK63S33/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":"2026-07-06T11:45:04Z","links":{"resolver":"https://pith.science/pith/XD27MZ74LOODBVCMJDOHK63S33","bundle":"https://pith.science/pith/XD27MZ74LOODBVCMJDOHK63S33/bundle.json","state":"https://pith.science/pith/XD27MZ74LOODBVCMJDOHK63S33/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XD27MZ74LOODBVCMJDOHK63S33/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XD27MZ74LOODBVCMJDOHK63S33","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":"30880fa73b09851d6ce3dd8d92b06b63ee602e021cc58256ec0e625e49320c37","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T02:41:36Z","title_canon_sha256":"bc91669e851a9fd128e4844f4b1eb9e82c87c61a4a894112028c291114d6a602"},"schema_version":"1.0","source":{"id":"2405.14114","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14114","created_at":"2026-07-05T08:24:06Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14114v2","created_at":"2026-07-05T08:24:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14114","created_at":"2026-07-05T08:24:06Z"},{"alias_kind":"pith_short_12","alias_value":"XD27MZ74LOOD","created_at":"2026-07-05T08:24:06Z"},{"alias_kind":"pith_short_16","alias_value":"XD27MZ74LOODBVCM","created_at":"2026-07-05T08:24:06Z"},{"alias_kind":"pith_short_8","alias_value":"XD27MZ74","created_at":"2026-07-05T08:24:06Z"}],"graph_snapshots":[{"event_id":"sha256:40651c7d36509e26143af36da2df32f0a5dcf337c11253c88ed93d452a02a742","target":"graph","created_at":"2026-07-05T08:24:06Z","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/2405.14114/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current Reinforcement Learning (RL) is often limited by the large amount of data needed to learn a successful policy. Offline RL aims to solve this issue by using transitions collected by a different behavior policy. We address a novel Offline RL problem setting in which, while collecting the dataset, the transition and reward functions gradually change between episodes but stay constant within each episode. We propose a method based on Contrastive Predictive Coding that identifies this non-stationarity in the offline dataset, accounts for it when training a policy, and predicts it during eval","authors_text":"Johannes Ackermann, Masashi Sugiyama, Takayuki Osa","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T02:41:36Z","title":"Offline Reinforcement Learning from Datasets with Structured Non-Stationarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14114","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:a4f6230efae9ef385938405a421b839c0f2ed0d552bfe3cdf7118f7d6e0423fc","target":"record","created_at":"2026-07-05T08:24:06Z","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":"30880fa73b09851d6ce3dd8d92b06b63ee602e021cc58256ec0e625e49320c37","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T02:41:36Z","title_canon_sha256":"bc91669e851a9fd128e4844f4b1eb9e82c87c61a4a894112028c291114d6a602"},"schema_version":"1.0","source":{"id":"2405.14114","kind":"arxiv","version":2}},"canonical_sha256":"b8f5f667fc5b9c30d44c48dc757b72deed88ef3223cf1c15cd2b55eff588b59c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8f5f667fc5b9c30d44c48dc757b72deed88ef3223cf1c15cd2b55eff588b59c","first_computed_at":"2026-07-05T08:24:06.172820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:06.172820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2vPPTNYPzHmiYTXEA4DtxuozzqyRtrDKFYdsa8gOA08mz4kKmkz/hCqMId2PDHEoCMY/q+CY1ETXLMGXpFqGBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:06.173360Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.14114","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4f6230efae9ef385938405a421b839c0f2ed0d552bfe3cdf7118f7d6e0423fc","sha256:40651c7d36509e26143af36da2df32f0a5dcf337c11253c88ed93d452a02a742"],"state_sha256":"54b5285e0909b601431736bd19b9075769fc77428f6133b3300281888b8e9c04"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bkCMH6ff/Q3aRurk3tEfKzTpIVqBNUVHr7B9uQTqIEid84sUkyRpeOe/3ial7F4OWRqbLy9KFs74+icgcxDNAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T11:45:04.654304Z","bundle_sha256":"02ee8d2b3905d8194ce78a549403c70a3dbc3e791cefe26670b9838e29badd0d"}}