{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:L7SQFY5RNFAPM725IKUNEBKQ2T","short_pith_number":"pith:L7SQFY5R","canonical_record":{"source":{"id":"2405.14183","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T05:27:51Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"7c672c7e4b7445e4f181bea8823886242c6b71334c8f665056b6dc7e7a4bfecb","abstract_canon_sha256":"5bad52014b695826f445975079ca528a0cd73baa84d27e138b3017f89f5347b6"},"schema_version":"1.0"},"canonical_sha256":"5fe502e3b16940f67f5d42a8d20550d4e6d56b2d9d7d598a6b9c2fa4d6a0bc48","source":{"kind":"arxiv","id":"2405.14183","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14183","created_at":"2026-07-05T09:28:49Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14183v2","created_at":"2026-07-05T09:28:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14183","created_at":"2026-07-05T09:28:49Z"},{"alias_kind":"pith_short_12","alias_value":"L7SQFY5RNFAP","created_at":"2026-07-05T09:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"L7SQFY5RNFAPM725","created_at":"2026-07-05T09:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"L7SQFY5R","created_at":"2026-07-05T09:28:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:L7SQFY5RNFAPM725IKUNEBKQ2T","target":"record","payload":{"canonical_record":{"source":{"id":"2405.14183","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T05:27:51Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"7c672c7e4b7445e4f181bea8823886242c6b71334c8f665056b6dc7e7a4bfecb","abstract_canon_sha256":"5bad52014b695826f445975079ca528a0cd73baa84d27e138b3017f89f5347b6"},"schema_version":"1.0"},"canonical_sha256":"5fe502e3b16940f67f5d42a8d20550d4e6d56b2d9d7d598a6b9c2fa4d6a0bc48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:49.862727Z","signature_b64":"tG3PdzulfusmZf/3QW+IE2HcFi1M4KRDvXgUvnGw7VCfu5kYkX38F94w44qM1U8ToXLiCEb6iphDLzPMVQjhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fe502e3b16940f67f5d42a8d20550d4e6d56b2d9d7d598a6b9c2fa4d6a0bc48","last_reissued_at":"2026-07-05T09:28:49.862251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:49.862251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.14183","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":"2026-07-05T09:28:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IN7OukwaRpgFOPNDWj1tuy0iuP7udPfmtyM2E4zAqHbzTfouv1hMIJ7HfupCGeOhbkEEVacsqfMtZx6YBTnzCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:18:13.432584Z"},"content_sha256":"cde501f5b1fad33fc4c54b919ea0d517d9e6e12edfcb766f085f4a1cf536b952","schema_version":"1.0","event_id":"sha256:cde501f5b1fad33fc4c54b919ea0d517d9e6e12edfcb766f085f4a1cf536b952"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:L7SQFY5RNFAPM725IKUNEBKQ2T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deterministic Policies for Constrained Reinforcement Learning in Polynomial Time","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Jeremy McMahan","submitted_at":"2024-05-23T05:27:51Z","abstract_excerpt":"We present a novel algorithm that efficiently computes near-optimal deterministic policies for constrained reinforcement learning (CRL) problems. Our approach combines three key ideas: (1) value-demand augmentation, (2) action-space approximate dynamic programming, and (3) time-space rounding. Our algorithm constitutes a fully polynomial-time approximation scheme (FPTAS) for any time-space recursive (TSR) cost criteria. A TSR criteria requires the cost of a policy to be computable recursively over both time and (state) space, which includes classical expectation, almost sure, and anytime const"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14183","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/2405.14183/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":"2026-07-05T09:28:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EQNdORPJQHGLA2eTVS74GQqZ6+P1lPsRof1HBzj7cNN2drEDc96922lbS62m1kZORAkbWmVyWzMkvCX7ZoYFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:18:13.433093Z"},"content_sha256":"58e0f2102e22c13b673516d0e5727c8d51b2802f6924b14d8d83f59c748b6724","schema_version":"1.0","event_id":"sha256:58e0f2102e22c13b673516d0e5727c8d51b2802f6924b14d8d83f59c748b6724"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L7SQFY5RNFAPM725IKUNEBKQ2T/bundle.json","state_url":"https://pith.science/pith/L7SQFY5RNFAPM725IKUNEBKQ2T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L7SQFY5RNFAPM725IKUNEBKQ2T/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":"2026-08-09T07:18:13Z","links":{"resolver":"https://pith.science/pith/L7SQFY5RNFAPM725IKUNEBKQ2T","bundle":"https://pith.science/pith/L7SQFY5RNFAPM725IKUNEBKQ2T/bundle.json","state":"https://pith.science/pith/L7SQFY5RNFAPM725IKUNEBKQ2T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L7SQFY5RNFAPM725IKUNEBKQ2T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L7SQFY5RNFAPM725IKUNEBKQ2T","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":"5bad52014b695826f445975079ca528a0cd73baa84d27e138b3017f89f5347b6","cross_cats_sorted":["cs.DS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T05:27:51Z","title_canon_sha256":"7c672c7e4b7445e4f181bea8823886242c6b71334c8f665056b6dc7e7a4bfecb"},"schema_version":"1.0","source":{"id":"2405.14183","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14183","created_at":"2026-07-05T09:28:49Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14183v2","created_at":"2026-07-05T09:28:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14183","created_at":"2026-07-05T09:28:49Z"},{"alias_kind":"pith_short_12","alias_value":"L7SQFY5RNFAP","created_at":"2026-07-05T09:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"L7SQFY5RNFAPM725","created_at":"2026-07-05T09:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"L7SQFY5R","created_at":"2026-07-05T09:28:49Z"}],"graph_snapshots":[{"event_id":"sha256:58e0f2102e22c13b673516d0e5727c8d51b2802f6924b14d8d83f59c748b6724","target":"graph","created_at":"2026-07-05T09:28:49Z","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/2405.14183/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel algorithm that efficiently computes near-optimal deterministic policies for constrained reinforcement learning (CRL) problems. Our approach combines three key ideas: (1) value-demand augmentation, (2) action-space approximate dynamic programming, and (3) time-space rounding. Our algorithm constitutes a fully polynomial-time approximation scheme (FPTAS) for any time-space recursive (TSR) cost criteria. A TSR criteria requires the cost of a policy to be computable recursively over both time and (state) space, which includes classical expectation, almost sure, and anytime const","authors_text":"Jeremy McMahan","cross_cats":["cs.DS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T05:27:51Z","title":"Deterministic Policies for Constrained Reinforcement Learning in Polynomial Time"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14183","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:cde501f5b1fad33fc4c54b919ea0d517d9e6e12edfcb766f085f4a1cf536b952","target":"record","created_at":"2026-07-05T09:28:49Z","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":"5bad52014b695826f445975079ca528a0cd73baa84d27e138b3017f89f5347b6","cross_cats_sorted":["cs.DS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T05:27:51Z","title_canon_sha256":"7c672c7e4b7445e4f181bea8823886242c6b71334c8f665056b6dc7e7a4bfecb"},"schema_version":"1.0","source":{"id":"2405.14183","kind":"arxiv","version":2}},"canonical_sha256":"5fe502e3b16940f67f5d42a8d20550d4e6d56b2d9d7d598a6b9c2fa4d6a0bc48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fe502e3b16940f67f5d42a8d20550d4e6d56b2d9d7d598a6b9c2fa4d6a0bc48","first_computed_at":"2026-07-05T09:28:49.862251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:49.862251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tG3PdzulfusmZf/3QW+IE2HcFi1M4KRDvXgUvnGw7VCfu5kYkX38F94w44qM1U8ToXLiCEb6iphDLzPMVQjhAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:49.862727Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.14183","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cde501f5b1fad33fc4c54b919ea0d517d9e6e12edfcb766f085f4a1cf536b952","sha256:58e0f2102e22c13b673516d0e5727c8d51b2802f6924b14d8d83f59c748b6724"],"state_sha256":"351f570018fb0030751fd00258bda5230989beddf0ae0128634c5e2f784c426b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9qsbxDhja3D1NJvrwT0V35DrmGL9yMcayh9mBBJ84bGe1n2kAqY4htsnh2OiXnutNc0237pQkBkolkTqF+AGAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:18:13.438425Z","bundle_sha256":"bf81f6537ce962a63420ef148afaecd794ef79af12c2c605676cd2e28db84d65"}}