{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:HMBDRT2CD4UFO7NX25TN4VVWWE","short_pith_number":"pith:HMBDRT2C","canonical_record":{"source":{"id":"2005.03718","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-07T19:38:09Z","cross_cats_sorted":["eess.SP","math.OC","stat.ML"],"title_canon_sha256":"70ffc5939935bdc3a3680667246ff6afeb271172a0e862f64d3e373828084ac7","abstract_canon_sha256":"9b884112698053d41d975ca536e6ff0ea64917571c782e76e17b62e29708d717"},"schema_version":"1.0"},"canonical_sha256":"3b0238cf421f28577db7d766de56b6b10f33e47b463b8ddae38b15c69625c459","source":{"kind":"arxiv","id":"2005.03718","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.03718","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"arxiv_version","alias_value":"2005.03718v1","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.03718","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"pith_short_12","alias_value":"HMBDRT2CD4UF","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"pith_short_16","alias_value":"HMBDRT2CD4UFO7NX","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"pith_short_8","alias_value":"HMBDRT2C","created_at":"2026-07-05T01:01:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:HMBDRT2CD4UFO7NX25TN4VVWWE","target":"record","payload":{"canonical_record":{"source":{"id":"2005.03718","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-07T19:38:09Z","cross_cats_sorted":["eess.SP","math.OC","stat.ML"],"title_canon_sha256":"70ffc5939935bdc3a3680667246ff6afeb271172a0e862f64d3e373828084ac7","abstract_canon_sha256":"9b884112698053d41d975ca536e6ff0ea64917571c782e76e17b62e29708d717"},"schema_version":"1.0"},"canonical_sha256":"3b0238cf421f28577db7d766de56b6b10f33e47b463b8ddae38b15c69625c459","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:01:25.300660Z","signature_b64":"BcWM0DlQsZyrLOseUSjXPu9PmVexVeVYTenkR6mRrEfkmt0jcO55ihE+8aOjVVqT01vHaSkpd+43N0YrqeUNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b0238cf421f28577db7d766de56b6b10f33e47b463b8ddae38b15c69625c459","last_reissued_at":"2026-07-05T01:01:25.300262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:01:25.300262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.03718","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":"2026-07-05T01:01:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YbAiDl3SufHxioJn42vk2hfSiXaUXdDaLpuSrjN1Z1h5YgtyDDiLUIIl6eg1SuYfz4LcLFMjJt1JYCeOs6XzAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T11:28:48.635284Z"},"content_sha256":"f32ed2036e6114faddee5a1b45399278304863c3ca6c42df9743cc0a8150f4cc","schema_version":"1.0","event_id":"sha256:f32ed2036e6114faddee5a1b45399278304863c3ca6c42df9743cc0a8150f4cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:HMBDRT2CD4UFO7NX25TN4VVWWE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Gradient-Aware Search Algorithm for Constrained Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.SP","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lin X. Cai, Prasanna Balaprakash, Sami Khairy","submitted_at":"2020-05-07T19:38:09Z","abstract_excerpt":"The canonical solution methodology for finite constrained Markov decision processes (CMDPs), where the objective is to maximize the expected infinite-horizon discounted rewards subject to the expected infinite-horizon discounted costs constraints, is based on convex linear programming. In this brief, we first prove that the optimization objective in the dual linear program of a finite CMDP is a piece-wise linear convex function (PWLC) with respect to the Lagrange penalty multipliers. Next, we propose a novel two-level Gradient-Aware Search (GAS) algorithm which exploits the PWLC structure to f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.03718","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/2005.03718/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":"2026-07-05T01:01:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qOlx/pYtrGNUM9zr2laTmH5YMJnU7Shx3K+Ayhl4Kt8X+TuaZMolQpJm8qLTuJaWMZuog949j3iOhXrDG5vWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T11:28:48.635803Z"},"content_sha256":"b508cf8fc8f46dc6d28ce52310304db7afca6913b5ec449852473b355e8cb25c","schema_version":"1.0","event_id":"sha256:b508cf8fc8f46dc6d28ce52310304db7afca6913b5ec449852473b355e8cb25c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HMBDRT2CD4UFO7NX25TN4VVWWE/bundle.json","state_url":"https://pith.science/pith/HMBDRT2CD4UFO7NX25TN4VVWWE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HMBDRT2CD4UFO7NX25TN4VVWWE/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":"2026-08-15T11:28:48Z","links":{"resolver":"https://pith.science/pith/HMBDRT2CD4UFO7NX25TN4VVWWE","bundle":"https://pith.science/pith/HMBDRT2CD4UFO7NX25TN4VVWWE/bundle.json","state":"https://pith.science/pith/HMBDRT2CD4UFO7NX25TN4VVWWE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HMBDRT2CD4UFO7NX25TN4VVWWE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HMBDRT2CD4UFO7NX25TN4VVWWE","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":"9b884112698053d41d975ca536e6ff0ea64917571c782e76e17b62e29708d717","cross_cats_sorted":["eess.SP","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-07T19:38:09Z","title_canon_sha256":"70ffc5939935bdc3a3680667246ff6afeb271172a0e862f64d3e373828084ac7"},"schema_version":"1.0","source":{"id":"2005.03718","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.03718","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"arxiv_version","alias_value":"2005.03718v1","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.03718","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"pith_short_12","alias_value":"HMBDRT2CD4UF","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"pith_short_16","alias_value":"HMBDRT2CD4UFO7NX","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"pith_short_8","alias_value":"HMBDRT2C","created_at":"2026-07-05T01:01:25Z"}],"graph_snapshots":[{"event_id":"sha256:b508cf8fc8f46dc6d28ce52310304db7afca6913b5ec449852473b355e8cb25c","target":"graph","created_at":"2026-07-05T01:01:25Z","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/2005.03718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The canonical solution methodology for finite constrained Markov decision processes (CMDPs), where the objective is to maximize the expected infinite-horizon discounted rewards subject to the expected infinite-horizon discounted costs constraints, is based on convex linear programming. In this brief, we first prove that the optimization objective in the dual linear program of a finite CMDP is a piece-wise linear convex function (PWLC) with respect to the Lagrange penalty multipliers. Next, we propose a novel two-level Gradient-Aware Search (GAS) algorithm which exploits the PWLC structure to f","authors_text":"Lin X. Cai, Prasanna Balaprakash, Sami Khairy","cross_cats":["eess.SP","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-07T19:38:09Z","title":"A Gradient-Aware Search Algorithm for Constrained Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.03718","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:f32ed2036e6114faddee5a1b45399278304863c3ca6c42df9743cc0a8150f4cc","target":"record","created_at":"2026-07-05T01:01:25Z","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":"9b884112698053d41d975ca536e6ff0ea64917571c782e76e17b62e29708d717","cross_cats_sorted":["eess.SP","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-07T19:38:09Z","title_canon_sha256":"70ffc5939935bdc3a3680667246ff6afeb271172a0e862f64d3e373828084ac7"},"schema_version":"1.0","source":{"id":"2005.03718","kind":"arxiv","version":1}},"canonical_sha256":"3b0238cf421f28577db7d766de56b6b10f33e47b463b8ddae38b15c69625c459","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b0238cf421f28577db7d766de56b6b10f33e47b463b8ddae38b15c69625c459","first_computed_at":"2026-07-05T01:01:25.300262Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:01:25.300262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BcWM0DlQsZyrLOseUSjXPu9PmVexVeVYTenkR6mRrEfkmt0jcO55ihE+8aOjVVqT01vHaSkpd+43N0YrqeUNBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:01:25.300660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.03718","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f32ed2036e6114faddee5a1b45399278304863c3ca6c42df9743cc0a8150f4cc","sha256:b508cf8fc8f46dc6d28ce52310304db7afca6913b5ec449852473b355e8cb25c"],"state_sha256":"fd037dd26ea25d9a0029517ef817fb1c41e74f70bef39cde01a60065161cb163"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"14Zmh22zHupUT8wcpCTj9JDjBxZEw/t68Ul9fqmwH25m1XBkcNmZQ7oiLiwCiLA+jEEX3445eYGBukJ6cvS2Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T11:28:48.641247Z","bundle_sha256":"f8c4e0dc49a530447d51feff3d17c82509c10b426f03328aac6638091f40eb5a"}}