{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CNNMOUWOJLZQ2DXA65GCSOTCQ3","short_pith_number":"pith:CNNMOUWO","canonical_record":{"source":{"id":"2404.04106","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-05T14:02:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dc38e95742b6b580473462f649b91ab0bd016bb83e3269314363c0cf463ad1c5","abstract_canon_sha256":"1b51405d32afbdde027fbe7f691042fe1a949b757cc0457593daca808af92ee9"},"schema_version":"1.0"},"canonical_sha256":"135ac752ce4af30d0ee0f74c293a6286c816a534544eeadc0d884cbcf82f6d3d","source":{"kind":"arxiv","id":"2404.04106","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04106","created_at":"2026-07-05T08:04:45Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04106v1","created_at":"2026-07-05T08:04:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04106","created_at":"2026-07-05T08:04:45Z"},{"alias_kind":"pith_short_12","alias_value":"CNNMOUWOJLZQ","created_at":"2026-07-05T08:04:45Z"},{"alias_kind":"pith_short_16","alias_value":"CNNMOUWOJLZQ2DXA","created_at":"2026-07-05T08:04:45Z"},{"alias_kind":"pith_short_8","alias_value":"CNNMOUWO","created_at":"2026-07-05T08:04:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CNNMOUWOJLZQ2DXA65GCSOTCQ3","target":"record","payload":{"canonical_record":{"source":{"id":"2404.04106","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-05T14:02:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dc38e95742b6b580473462f649b91ab0bd016bb83e3269314363c0cf463ad1c5","abstract_canon_sha256":"1b51405d32afbdde027fbe7f691042fe1a949b757cc0457593daca808af92ee9"},"schema_version":"1.0"},"canonical_sha256":"135ac752ce4af30d0ee0f74c293a6286c816a534544eeadc0d884cbcf82f6d3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:45.622517Z","signature_b64":"ZPPtdXYI01PwnH4//y8hoo9zv6kPn8v/ifw14AxlNjpurS/OOgMdYhPST0UBRPpAbRS+VhNT8daCK0+BXM+HBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"135ac752ce4af30d0ee0f74c293a6286c816a534544eeadc0d884cbcf82f6d3d","last_reissued_at":"2026-07-05T08:04:45.622039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:45.622039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.04106","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":"2026-07-05T08:04:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E0y4o2ZpzSToQlXu5PMtXjJZAB37aNutKbnSwJWQRDqhav9dsXGbACp1LFvAUCofWmFYJWB2wyScD97biPCTCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:35:28.044725Z"},"content_sha256":"f177c4cfb6cae657c57357e7a43a5523fac70c459dc9a6f4bb8244975a013733","schema_version":"1.0","event_id":"sha256:f177c4cfb6cae657c57357e7a43a5523fac70c459dc9a6f4bb8244975a013733"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CNNMOUWOJLZQ2DXA65GCSOTCQ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Intervention-Assisted Policy Gradient Methods for Online Stochastic Queuing Network Optimization: Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Brooke Shrader, Eytan Modiano, Jerrod Wigmore","submitted_at":"2024-04-05T14:02:04Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) offers a powerful approach to training neural network control policies for stochastic queuing networks (SQN). However, traditional DRL methods rely on offline simulations or static datasets, limiting their real-world application in SQN control. This work proposes Online Deep Reinforcement Learning-based Controls (ODRLC) as an alternative, where an intelligent agent interacts directly with a real environment and learns an optimal control policy from these online interactions. SQNs present a challenge for ODRLC due to the unbounded nature of the queues within th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04106","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/2404.04106/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":"2026-07-05T08:04:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ioN673ji3rPIbpKqZKY7P9wC4A/wX+oucz3ltReoH1tWT1xjgyYLfLdrrIAUL8q2u6A6th5cLW0pueszEepXAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:35:28.048897Z"},"content_sha256":"5046788bbb29f3c0e4e158b8e49a26ff2b7949aeb4b4b9d7949552c35e5b44bd","schema_version":"1.0","event_id":"sha256:5046788bbb29f3c0e4e158b8e49a26ff2b7949aeb4b4b9d7949552c35e5b44bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CNNMOUWOJLZQ2DXA65GCSOTCQ3/bundle.json","state_url":"https://pith.science/pith/CNNMOUWOJLZQ2DXA65GCSOTCQ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CNNMOUWOJLZQ2DXA65GCSOTCQ3/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":"2026-08-17T15:35:28Z","links":{"resolver":"https://pith.science/pith/CNNMOUWOJLZQ2DXA65GCSOTCQ3","bundle":"https://pith.science/pith/CNNMOUWOJLZQ2DXA65GCSOTCQ3/bundle.json","state":"https://pith.science/pith/CNNMOUWOJLZQ2DXA65GCSOTCQ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CNNMOUWOJLZQ2DXA65GCSOTCQ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CNNMOUWOJLZQ2DXA65GCSOTCQ3","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":"1b51405d32afbdde027fbe7f691042fe1a949b757cc0457593daca808af92ee9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-05T14:02:04Z","title_canon_sha256":"dc38e95742b6b580473462f649b91ab0bd016bb83e3269314363c0cf463ad1c5"},"schema_version":"1.0","source":{"id":"2404.04106","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04106","created_at":"2026-07-05T08:04:45Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04106v1","created_at":"2026-07-05T08:04:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04106","created_at":"2026-07-05T08:04:45Z"},{"alias_kind":"pith_short_12","alias_value":"CNNMOUWOJLZQ","created_at":"2026-07-05T08:04:45Z"},{"alias_kind":"pith_short_16","alias_value":"CNNMOUWOJLZQ2DXA","created_at":"2026-07-05T08:04:45Z"},{"alias_kind":"pith_short_8","alias_value":"CNNMOUWO","created_at":"2026-07-05T08:04:45Z"}],"graph_snapshots":[{"event_id":"sha256:5046788bbb29f3c0e4e158b8e49a26ff2b7949aeb4b4b9d7949552c35e5b44bd","target":"graph","created_at":"2026-07-05T08:04:45Z","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/2404.04106/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Reinforcement Learning (DRL) offers a powerful approach to training neural network control policies for stochastic queuing networks (SQN). However, traditional DRL methods rely on offline simulations or static datasets, limiting their real-world application in SQN control. This work proposes Online Deep Reinforcement Learning-based Controls (ODRLC) as an alternative, where an intelligent agent interacts directly with a real environment and learns an optimal control policy from these online interactions. SQNs present a challenge for ODRLC due to the unbounded nature of the queues within th","authors_text":"Brooke Shrader, Eytan Modiano, Jerrod Wigmore","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-05T14:02:04Z","title":"Intervention-Assisted Policy Gradient Methods for Online Stochastic Queuing Network Optimization: Technical Report"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04106","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:f177c4cfb6cae657c57357e7a43a5523fac70c459dc9a6f4bb8244975a013733","target":"record","created_at":"2026-07-05T08:04:45Z","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":"1b51405d32afbdde027fbe7f691042fe1a949b757cc0457593daca808af92ee9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-05T14:02:04Z","title_canon_sha256":"dc38e95742b6b580473462f649b91ab0bd016bb83e3269314363c0cf463ad1c5"},"schema_version":"1.0","source":{"id":"2404.04106","kind":"arxiv","version":1}},"canonical_sha256":"135ac752ce4af30d0ee0f74c293a6286c816a534544eeadc0d884cbcf82f6d3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"135ac752ce4af30d0ee0f74c293a6286c816a534544eeadc0d884cbcf82f6d3d","first_computed_at":"2026-07-05T08:04:45.622039Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:04:45.622039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZPPtdXYI01PwnH4//y8hoo9zv6kPn8v/ifw14AxlNjpurS/OOgMdYhPST0UBRPpAbRS+VhNT8daCK0+BXM+HBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:04:45.622517Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.04106","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f177c4cfb6cae657c57357e7a43a5523fac70c459dc9a6f4bb8244975a013733","sha256:5046788bbb29f3c0e4e158b8e49a26ff2b7949aeb4b4b9d7949552c35e5b44bd"],"state_sha256":"ab2f08ef3d70c10f8b7baba41361abe6978b5fa87e5185c67ff392617d73c125"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EP2TqYqYsNPPS8sLg0GxmkiZJdY8s7lWTm+lNyu3fKpkf6RbnZcfg40OMBJb37thBFSqgEOOtTuZjCBIKp2KAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T15:35:28.055297Z","bundle_sha256":"57a4de8b944f7893228b6a73af18950d54c177ccadda4b205a588669902363ba"}}