{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:IJZCKUTI67UNMOEJWUQQBMNEWN","short_pith_number":"pith:IJZCKUTI","canonical_record":{"source":{"id":"2006.05051","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-09T05:02:44Z","cross_cats_sorted":["cs.AI","cs.DS","stat.ML"],"title_canon_sha256":"459b200c4228f326767fc2b763745cf955d64ffa788b13aae5765f083f953c45","abstract_canon_sha256":"ca403d9e0966955937707c932107915e5b0353198443a087572fb142cf5dadce"},"schema_version":"1.0"},"canonical_sha256":"4272255268f7e8d63889b52100b1a4b348a9ef22c845bb215ea1b847e6839b79","source":{"kind":"arxiv","id":"2006.05051","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.05051","created_at":"2026-07-05T02:46:23Z"},{"alias_kind":"arxiv_version","alias_value":"2006.05051v2","created_at":"2026-07-05T02:46:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05051","created_at":"2026-07-05T02:46:23Z"},{"alias_kind":"pith_short_12","alias_value":"IJZCKUTI67UN","created_at":"2026-07-05T02:46:23Z"},{"alias_kind":"pith_short_16","alias_value":"IJZCKUTI67UNMOEJ","created_at":"2026-07-05T02:46:23Z"},{"alias_kind":"pith_short_8","alias_value":"IJZCKUTI","created_at":"2026-07-05T02:46:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:IJZCKUTI67UNMOEJWUQQBMNEWN","target":"record","payload":{"canonical_record":{"source":{"id":"2006.05051","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-09T05:02:44Z","cross_cats_sorted":["cs.AI","cs.DS","stat.ML"],"title_canon_sha256":"459b200c4228f326767fc2b763745cf955d64ffa788b13aae5765f083f953c45","abstract_canon_sha256":"ca403d9e0966955937707c932107915e5b0353198443a087572fb142cf5dadce"},"schema_version":"1.0"},"canonical_sha256":"4272255268f7e8d63889b52100b1a4b348a9ef22c845bb215ea1b847e6839b79","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:23.793068Z","signature_b64":"Fm2B3n9o+Ar1FFoOghW28pj4vo1ewTwV/HfRUIAJoS4CEH7iIk4IH+AS11cv1Wmt+TIYcMGF0kvatsT1sNncBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4272255268f7e8d63889b52100b1a4b348a9ef22c845bb215ea1b847e6839b79","last_reissued_at":"2026-07-05T02:46:23.792557Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:23.792557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.05051","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":"2026-07-05T02:46:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zdi/ku89pDAnoNXyG8dDstrQc2nVzjLuS+pA9nCdfOalufAVkzvf0cAN4Nlo6yP1O7z91cDQQOb39Jgv5vEMCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:27:56.553537Z"},"content_sha256":"eac2e4087ae9bda900f1f529fca72d99fc44dfe95afbbff028c3f7ff9277d893","schema_version":"1.0","event_id":"sha256:eac2e4087ae9bda900f1f529fca72d99fc44dfe95afbbff028c3f7ff9277d893"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:IJZCKUTI67UNMOEJWUQQBMNEWN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Constrained episodic reinforcement learning in concave-convex and knapsack settings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aleksandrs Slivkins, Kiant\\'e Brantley, Max Simchowitz, Miroslav Dudik, Sobhan Miryoosefi, Thodoris Lykouris, Wen Sun","submitted_at":"2020-06-09T05:02:44Z","abstract_excerpt":"We propose an algorithm for tabular episodic reinforcement learning with constraints. We provide a modular analysis with strong theoretical guarantees for settings with concave rewards and convex constraints, and for settings with hard constraints (knapsacks). Most of the previous work in constrained reinforcement learning is limited to linear constraints, and the remaining work focuses on either the feasibility question or settings with a single episode. Our experiments demonstrate that the proposed algorithm significantly outperforms these approaches in existing constrained episodic environm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05051","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/2006.05051/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":"2026-07-05T02:46:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8j1QTiasmq52RX7/NhoVKrmm1elqFUtZTGwGC649gdhKNse9XxNT5bAm2Nn2mYXm15ZsyKqSeMOjOXa8eroKAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:27:56.554077Z"},"content_sha256":"dd5f17739686121d691ad1b513630d21f72ad82fe677a68e9ceddad5d0d0151f","schema_version":"1.0","event_id":"sha256:dd5f17739686121d691ad1b513630d21f72ad82fe677a68e9ceddad5d0d0151f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IJZCKUTI67UNMOEJWUQQBMNEWN/bundle.json","state_url":"https://pith.science/pith/IJZCKUTI67UNMOEJWUQQBMNEWN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IJZCKUTI67UNMOEJWUQQBMNEWN/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":"2026-08-16T22:27:56Z","links":{"resolver":"https://pith.science/pith/IJZCKUTI67UNMOEJWUQQBMNEWN","bundle":"https://pith.science/pith/IJZCKUTI67UNMOEJWUQQBMNEWN/bundle.json","state":"https://pith.science/pith/IJZCKUTI67UNMOEJWUQQBMNEWN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IJZCKUTI67UNMOEJWUQQBMNEWN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IJZCKUTI67UNMOEJWUQQBMNEWN","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":"ca403d9e0966955937707c932107915e5b0353198443a087572fb142cf5dadce","cross_cats_sorted":["cs.AI","cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-09T05:02:44Z","title_canon_sha256":"459b200c4228f326767fc2b763745cf955d64ffa788b13aae5765f083f953c45"},"schema_version":"1.0","source":{"id":"2006.05051","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.05051","created_at":"2026-07-05T02:46:23Z"},{"alias_kind":"arxiv_version","alias_value":"2006.05051v2","created_at":"2026-07-05T02:46:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05051","created_at":"2026-07-05T02:46:23Z"},{"alias_kind":"pith_short_12","alias_value":"IJZCKUTI67UN","created_at":"2026-07-05T02:46:23Z"},{"alias_kind":"pith_short_16","alias_value":"IJZCKUTI67UNMOEJ","created_at":"2026-07-05T02:46:23Z"},{"alias_kind":"pith_short_8","alias_value":"IJZCKUTI","created_at":"2026-07-05T02:46:23Z"}],"graph_snapshots":[{"event_id":"sha256:dd5f17739686121d691ad1b513630d21f72ad82fe677a68e9ceddad5d0d0151f","target":"graph","created_at":"2026-07-05T02:46:23Z","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/2006.05051/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose an algorithm for tabular episodic reinforcement learning with constraints. We provide a modular analysis with strong theoretical guarantees for settings with concave rewards and convex constraints, and for settings with hard constraints (knapsacks). Most of the previous work in constrained reinforcement learning is limited to linear constraints, and the remaining work focuses on either the feasibility question or settings with a single episode. Our experiments demonstrate that the proposed algorithm significantly outperforms these approaches in existing constrained episodic environm","authors_text":"Aleksandrs Slivkins, Kiant\\'e Brantley, Max Simchowitz, Miroslav Dudik, Sobhan Miryoosefi, Thodoris Lykouris, Wen Sun","cross_cats":["cs.AI","cs.DS","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-09T05:02:44Z","title":"Constrained episodic reinforcement learning in concave-convex and knapsack settings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05051","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:eac2e4087ae9bda900f1f529fca72d99fc44dfe95afbbff028c3f7ff9277d893","target":"record","created_at":"2026-07-05T02:46:23Z","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":"ca403d9e0966955937707c932107915e5b0353198443a087572fb142cf5dadce","cross_cats_sorted":["cs.AI","cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-09T05:02:44Z","title_canon_sha256":"459b200c4228f326767fc2b763745cf955d64ffa788b13aae5765f083f953c45"},"schema_version":"1.0","source":{"id":"2006.05051","kind":"arxiv","version":2}},"canonical_sha256":"4272255268f7e8d63889b52100b1a4b348a9ef22c845bb215ea1b847e6839b79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4272255268f7e8d63889b52100b1a4b348a9ef22c845bb215ea1b847e6839b79","first_computed_at":"2026-07-05T02:46:23.792557Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:46:23.792557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fm2B3n9o+Ar1FFoOghW28pj4vo1ewTwV/HfRUIAJoS4CEH7iIk4IH+AS11cv1Wmt+TIYcMGF0kvatsT1sNncBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:46:23.793068Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.05051","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eac2e4087ae9bda900f1f529fca72d99fc44dfe95afbbff028c3f7ff9277d893","sha256:dd5f17739686121d691ad1b513630d21f72ad82fe677a68e9ceddad5d0d0151f"],"state_sha256":"ea46c0631fe658d69b9598097257591054242310d5fc8d802dba6472bc1fb1f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ra60WxTGRWiWpOlPtH1laDsi4lGSwzt1pKs3f1IgS7iS9ixsCD4xtb6afv9as8Qb5/b8rrEXzReLGXL5IXNBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T22:27:56.559014Z","bundle_sha256":"c18d9b686af388ef61483f2419b73d160726573d38610074e691c6dd26f7dbc0"}}