{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RYSYDD7H3PBTUH3WWEAIBM5WOX","short_pith_number":"pith:RYSYDD7H","canonical_record":{"source":{"id":"2412.18946","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-25T16:42:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0c9e252e09a6595ca1401c5b89c8c737b9e1590051a07a16dc8d140187996c47","abstract_canon_sha256":"8d85e4444c4ee042afe64ea3cf6c5b77ad1a36241b1430bf25736343d02cbad5"},"schema_version":"1.0"},"canonical_sha256":"8e25818fe7dbc33a1f76b10080b3b675e1e888194b8e601bf667900de72910aa","source":{"kind":"arxiv","id":"2412.18946","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18946","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18946v2","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18946","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"RYSYDD7H3PBT","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"pith_short_16","alias_value":"RYSYDD7H3PBTUH3W","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"pith_short_8","alias_value":"RYSYDD7H","created_at":"2026-07-05T11:10:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RYSYDD7H3PBTUH3WWEAIBM5WOX","target":"record","payload":{"canonical_record":{"source":{"id":"2412.18946","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-25T16:42:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0c9e252e09a6595ca1401c5b89c8c737b9e1590051a07a16dc8d140187996c47","abstract_canon_sha256":"8d85e4444c4ee042afe64ea3cf6c5b77ad1a36241b1430bf25736343d02cbad5"},"schema_version":"1.0"},"canonical_sha256":"8e25818fe7dbc33a1f76b10080b3b675e1e888194b8e601bf667900de72910aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:49.976645Z","signature_b64":"vsrVdXTmcujKWkId2FKY4hHgHM92A8BrXB/Mg8oBznwP2npw22lM1FtLaVBgT40uRkf2y9j4tMPK4JeKEeelCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e25818fe7dbc33a1f76b10080b3b675e1e888194b8e601bf667900de72910aa","last_reissued_at":"2026-07-05T11:10:49.976097Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:49.976097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.18946","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":"2026-07-05T11:10:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nrZOJs5zHWa3l+uFBjsntGs38CIeFjNhf+EuWRkYJ9Rb5xvLC1BwRh6KE39EBVIhSUNEcXdsl8WIueskRLRJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T22:56:38.090113Z"},"content_sha256":"598f3be763cf99dbe33eb77f585032a4b9304272c03a1428077ed70b471922b0","schema_version":"1.0","event_id":"sha256:598f3be763cf99dbe33eb77f585032a4b9304272c03a1428077ed70b471922b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RYSYDD7H3PBTUH3WWEAIBM5WOX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alan Fern, Aryan Deshwal, Honghao Wei, Janardhan Rao Doppa, Yassine Chemingui","submitted_at":"2024-12-25T16:42:27Z","abstract_excerpt":"Offline safe reinforcement learning (OSRL) involves learning a decision-making policy to maximize rewards from a fixed batch of training data to satisfy pre-defined safety constraints. However, adapting to varying safety constraints during deployment without retraining remains an under-explored challenge. To address this challenge, we introduce constraint-adaptive policy switching (CAPS), a wrapper framework around existing offline RL algorithms. During training, CAPS uses offline data to learn multiple policies with a shared representation that optimize different reward and cost trade-offs. D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18946","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/2412.18946/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":"2026-07-05T11:10:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qw1AQDgM86AZNy7LFau+cxE/+fdNyPDWUUes2r6iQmaiDNrpjr7IoQq5hN0IWxvNaCdAtyIctV3svJHyXawtAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T22:56:38.091050Z"},"content_sha256":"5a6761265c9592ba6f1ffa06ae4762ce4eb6f0912b9abb46eb31ca4ff6387318","schema_version":"1.0","event_id":"sha256:5a6761265c9592ba6f1ffa06ae4762ce4eb6f0912b9abb46eb31ca4ff6387318"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RYSYDD7H3PBTUH3WWEAIBM5WOX/bundle.json","state_url":"https://pith.science/pith/RYSYDD7H3PBTUH3WWEAIBM5WOX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RYSYDD7H3PBTUH3WWEAIBM5WOX/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":"2026-08-23T22:56:38Z","links":{"resolver":"https://pith.science/pith/RYSYDD7H3PBTUH3WWEAIBM5WOX","bundle":"https://pith.science/pith/RYSYDD7H3PBTUH3WWEAIBM5WOX/bundle.json","state":"https://pith.science/pith/RYSYDD7H3PBTUH3WWEAIBM5WOX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RYSYDD7H3PBTUH3WWEAIBM5WOX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RYSYDD7H3PBTUH3WWEAIBM5WOX","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":"8d85e4444c4ee042afe64ea3cf6c5b77ad1a36241b1430bf25736343d02cbad5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-25T16:42:27Z","title_canon_sha256":"0c9e252e09a6595ca1401c5b89c8c737b9e1590051a07a16dc8d140187996c47"},"schema_version":"1.0","source":{"id":"2412.18946","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18946","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18946v2","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18946","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"RYSYDD7H3PBT","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"pith_short_16","alias_value":"RYSYDD7H3PBTUH3W","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"pith_short_8","alias_value":"RYSYDD7H","created_at":"2026-07-05T11:10:49Z"}],"graph_snapshots":[{"event_id":"sha256:5a6761265c9592ba6f1ffa06ae4762ce4eb6f0912b9abb46eb31ca4ff6387318","target":"graph","created_at":"2026-07-05T11:10:49Z","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/2412.18946/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline safe reinforcement learning (OSRL) involves learning a decision-making policy to maximize rewards from a fixed batch of training data to satisfy pre-defined safety constraints. However, adapting to varying safety constraints during deployment without retraining remains an under-explored challenge. To address this challenge, we introduce constraint-adaptive policy switching (CAPS), a wrapper framework around existing offline RL algorithms. During training, CAPS uses offline data to learn multiple policies with a shared representation that optimize different reward and cost trade-offs. D","authors_text":"Alan Fern, Aryan Deshwal, Honghao Wei, Janardhan Rao Doppa, Yassine Chemingui","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-25T16:42:27Z","title":"Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18946","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":"sha256:598f3be763cf99dbe33eb77f585032a4b9304272c03a1428077ed70b471922b0","target":"record","created_at":"2026-07-05T11:10:49Z","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":"8d85e4444c4ee042afe64ea3cf6c5b77ad1a36241b1430bf25736343d02cbad5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-25T16:42:27Z","title_canon_sha256":"0c9e252e09a6595ca1401c5b89c8c737b9e1590051a07a16dc8d140187996c47"},"schema_version":"1.0","source":{"id":"2412.18946","kind":"arxiv","version":2}},"canonical_sha256":"8e25818fe7dbc33a1f76b10080b3b675e1e888194b8e601bf667900de72910aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e25818fe7dbc33a1f76b10080b3b675e1e888194b8e601bf667900de72910aa","first_computed_at":"2026-07-05T11:10:49.976097Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:49.976097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vsrVdXTmcujKWkId2FKY4hHgHM92A8BrXB/Mg8oBznwP2npw22lM1FtLaVBgT40uRkf2y9j4tMPK4JeKEeelCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:49.976645Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18946","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:598f3be763cf99dbe33eb77f585032a4b9304272c03a1428077ed70b471922b0","sha256:5a6761265c9592ba6f1ffa06ae4762ce4eb6f0912b9abb46eb31ca4ff6387318"],"state_sha256":"501bc5eedc70e8bd35f498f7b65ed962dde58ec5aaf5a3f834e783e6c45e7575"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sdZv0Qf1QNbRpUBRUvB9JEkb9OrKfbcMO+tatDkEjHdUsDDa9QAJgEt3arMnc6qyO0LaDCi8djwgPnKZGGz2CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T22:56:38.097137Z","bundle_sha256":"cdc63671310a75b1304994d7439a9363ed87010d843bae0a6210529447836b46"}}