{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OP2S6D4VQ52FSAMJNPA4LJX2R7","short_pith_number":"pith:OP2S6D4V","canonical_record":{"source":{"id":"2304.03104","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-05T15:49:51Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"5bc111e2f59afda7166909198c7053bb813108c358a3eb97b60081541e00a902","abstract_canon_sha256":"e127bb1f60e5bb02015694b629d11765bf2e2209255efc65583a3e0555b95aa6"},"schema_version":"1.0"},"canonical_sha256":"73f52f0f9587745901896bc1c5a6fa8fd14364f8ffb41622edb2fb8416693ffb","source":{"kind":"arxiv","id":"2304.03104","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03104","created_at":"2026-07-05T05:58:45Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03104v1","created_at":"2026-07-05T05:58:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03104","created_at":"2026-07-05T05:58:45Z"},{"alias_kind":"pith_short_12","alias_value":"OP2S6D4VQ52F","created_at":"2026-07-05T05:58:45Z"},{"alias_kind":"pith_short_16","alias_value":"OP2S6D4VQ52FSAMJ","created_at":"2026-07-05T05:58:45Z"},{"alias_kind":"pith_short_8","alias_value":"OP2S6D4V","created_at":"2026-07-05T05:58:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OP2S6D4VQ52FSAMJNPA4LJX2R7","target":"record","payload":{"canonical_record":{"source":{"id":"2304.03104","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-05T15:49:51Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"5bc111e2f59afda7166909198c7053bb813108c358a3eb97b60081541e00a902","abstract_canon_sha256":"e127bb1f60e5bb02015694b629d11765bf2e2209255efc65583a3e0555b95aa6"},"schema_version":"1.0"},"canonical_sha256":"73f52f0f9587745901896bc1c5a6fa8fd14364f8ffb41622edb2fb8416693ffb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:45.181368Z","signature_b64":"SlDee1kT3HNfLVZY76D6co3VQY5JKYGpAijhxRiVbL/NaM5VjIEPUYz0v194fcma4f3ldhQFW6k1pzDqvp5jDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73f52f0f9587745901896bc1c5a6fa8fd14364f8ffb41622edb2fb8416693ffb","last_reissued_at":"2026-07-05T05:58:45.181021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:45.181021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.03104","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:58:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hT+pimPf7KDsULvZyRy5NgmaJh+ZO15iPBDW7NZoCJTtfERlWC5TM+SscC2Q3T4OGjqc4/tDbnwpHkxY6U9ECA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:48:16.427255Z"},"content_sha256":"10fbdd85af6415539f0ef72de7f0dc64be2d91bd7f6909daa76c490c746d0124","schema_version":"1.0","event_id":"sha256:10fbdd85af6415539f0ef72de7f0dc64be2d91bd7f6909daa76c490c746d0124"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OP2S6D4VQ52FSAMJNPA4LJX2R7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Constrained Exploration in Reinforcement Learning with Optimality Preservation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Peter C. Y. Chen","submitted_at":"2023-04-05T15:49:51Z","abstract_excerpt":"We consider a class of reinforcement-learning systems in which the agent follows a behavior policy to explore a discrete state-action space to find an optimal policy while adhering to some restriction on its behavior. Such restriction may prevent the agent from visiting some state-action pairs, possibly leading to the agent finding only a sub-optimal policy. To address this problem we introduce the concept of constrained exploration with optimality preservation, whereby the exploration behavior of the agent is constrained to meet a specification while the optimality of the (original) unconstra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03104","kind":"arxiv","version":1},"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/2304.03104/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":"2026-07-05T05:58:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5b0ELC50XH1DImLgFg4fqSJOnc4koICxVX1XmlodHHF6uK5YUZTg0HFyTb/zCD+58FekS/zs0X3RHRpr96bADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:48:16.427951Z"},"content_sha256":"43d7a1a58cf40b221c06ab7469639eb71b0a14af76e47d0301dddfb64340463a","schema_version":"1.0","event_id":"sha256:43d7a1a58cf40b221c06ab7469639eb71b0a14af76e47d0301dddfb64340463a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OP2S6D4VQ52FSAMJNPA4LJX2R7/bundle.json","state_url":"https://pith.science/pith/OP2S6D4VQ52FSAMJNPA4LJX2R7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OP2S6D4VQ52FSAMJNPA4LJX2R7/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":"2026-07-05T15:48:16Z","links":{"resolver":"https://pith.science/pith/OP2S6D4VQ52FSAMJNPA4LJX2R7","bundle":"https://pith.science/pith/OP2S6D4VQ52FSAMJNPA4LJX2R7/bundle.json","state":"https://pith.science/pith/OP2S6D4VQ52FSAMJNPA4LJX2R7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OP2S6D4VQ52FSAMJNPA4LJX2R7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OP2S6D4VQ52FSAMJNPA4LJX2R7","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":"e127bb1f60e5bb02015694b629d11765bf2e2209255efc65583a3e0555b95aa6","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-05T15:49:51Z","title_canon_sha256":"5bc111e2f59afda7166909198c7053bb813108c358a3eb97b60081541e00a902"},"schema_version":"1.0","source":{"id":"2304.03104","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03104","created_at":"2026-07-05T05:58:45Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03104v1","created_at":"2026-07-05T05:58:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03104","created_at":"2026-07-05T05:58:45Z"},{"alias_kind":"pith_short_12","alias_value":"OP2S6D4VQ52F","created_at":"2026-07-05T05:58:45Z"},{"alias_kind":"pith_short_16","alias_value":"OP2S6D4VQ52FSAMJ","created_at":"2026-07-05T05:58:45Z"},{"alias_kind":"pith_short_8","alias_value":"OP2S6D4V","created_at":"2026-07-05T05:58:45Z"}],"graph_snapshots":[{"event_id":"sha256:43d7a1a58cf40b221c06ab7469639eb71b0a14af76e47d0301dddfb64340463a","target":"graph","created_at":"2026-07-05T05:58:45Z","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/2304.03104/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider a class of reinforcement-learning systems in which the agent follows a behavior policy to explore a discrete state-action space to find an optimal policy while adhering to some restriction on its behavior. Such restriction may prevent the agent from visiting some state-action pairs, possibly leading to the agent finding only a sub-optimal policy. To address this problem we introduce the concept of constrained exploration with optimality preservation, whereby the exploration behavior of the agent is constrained to meet a specification while the optimality of the (original) unconstra","authors_text":"Peter C. Y. Chen","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-05T15:49:51Z","title":"Constrained Exploration in Reinforcement Learning with Optimality Preservation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03104","kind":"arxiv","version":1},"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":"sha256:10fbdd85af6415539f0ef72de7f0dc64be2d91bd7f6909daa76c490c746d0124","target":"record","created_at":"2026-07-05T05:58:45Z","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":"e127bb1f60e5bb02015694b629d11765bf2e2209255efc65583a3e0555b95aa6","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-05T15:49:51Z","title_canon_sha256":"5bc111e2f59afda7166909198c7053bb813108c358a3eb97b60081541e00a902"},"schema_version":"1.0","source":{"id":"2304.03104","kind":"arxiv","version":1}},"canonical_sha256":"73f52f0f9587745901896bc1c5a6fa8fd14364f8ffb41622edb2fb8416693ffb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73f52f0f9587745901896bc1c5a6fa8fd14364f8ffb41622edb2fb8416693ffb","first_computed_at":"2026-07-05T05:58:45.181021Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:58:45.181021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SlDee1kT3HNfLVZY76D6co3VQY5JKYGpAijhxRiVbL/NaM5VjIEPUYz0v194fcma4f3ldhQFW6k1pzDqvp5jDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:58:45.181368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.03104","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10fbdd85af6415539f0ef72de7f0dc64be2d91bd7f6909daa76c490c746d0124","sha256:43d7a1a58cf40b221c06ab7469639eb71b0a14af76e47d0301dddfb64340463a"],"state_sha256":"f9b8c4fdbad7267b337a362f550d81799a7a7f65a54ac60dcc1dd01692697242"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UmYnpkMM2p7DvHmakgixMvHU/28tOziB+LKXPYusvC0xlMwrwTtN/a6l1GriUsDqNcxBEET4MGsa0RRTgDs6DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T15:48:16.431475Z","bundle_sha256":"d6c82898359009c4f4473c2c3813d499a245649d42f7b0ba910235517aca7df3"}}