{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SZHIKSAJQCQSOMDS6DG2YH5CYR","short_pith_number":"pith:SZHIKSAJ","canonical_record":{"source":{"id":"2410.14606","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-18T17:00:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fc20dc22f847c194fcd1a7e68d65b3b8d96a2d8c4a6dc163b34ff05c26f3c2ea","abstract_canon_sha256":"5a6cdda6afc66a7df532a0d4fa7565f8b9ccee7abff8bb55f64dbf08c3b75612"},"schema_version":"1.0"},"canonical_sha256":"964e85480980a1273072f0cdac1fa2c4687fc6d57e75d1f51aadfed83c0797c3","source":{"kind":"arxiv","id":"2410.14606","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14606","created_at":"2026-07-05T09:45:15Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14606v2","created_at":"2026-07-05T09:45:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14606","created_at":"2026-07-05T09:45:15Z"},{"alias_kind":"pith_short_12","alias_value":"SZHIKSAJQCQS","created_at":"2026-07-05T09:45:15Z"},{"alias_kind":"pith_short_16","alias_value":"SZHIKSAJQCQSOMDS","created_at":"2026-07-05T09:45:15Z"},{"alias_kind":"pith_short_8","alias_value":"SZHIKSAJ","created_at":"2026-07-05T09:45:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SZHIKSAJQCQSOMDS6DG2YH5CYR","target":"record","payload":{"canonical_record":{"source":{"id":"2410.14606","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-18T17:00:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fc20dc22f847c194fcd1a7e68d65b3b8d96a2d8c4a6dc163b34ff05c26f3c2ea","abstract_canon_sha256":"5a6cdda6afc66a7df532a0d4fa7565f8b9ccee7abff8bb55f64dbf08c3b75612"},"schema_version":"1.0"},"canonical_sha256":"964e85480980a1273072f0cdac1fa2c4687fc6d57e75d1f51aadfed83c0797c3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:15.519166Z","signature_b64":"Ii7xeV69E2AgUP4et030WBigw/Xh7We/GiU56JTudP+to48qP71r5MA5bFC8mHjZRRBLjq9WVly02foNl6iJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"964e85480980a1273072f0cdac1fa2c4687fc6d57e75d1f51aadfed83c0797c3","last_reissued_at":"2026-07-05T09:45:15.518698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:15.518698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.14606","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":"2026-07-05T09:45:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M+wOZzT2pQUe37nqsU2YXw3/afuv59LSl6Nn4kardP1fXoIJpmMQbxn1ZsoGRA/Lb0MIFiUYpaKXzZSCtPfsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:14:24.462750Z"},"content_sha256":"4707cb4fff618655198359cd7eaf920681729a53555fd8d5121bc657bbed085a","schema_version":"1.0","event_id":"sha256:4707cb4fff618655198359cd7eaf920681729a53555fd8d5121bc657bbed085a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SZHIKSAJQCQSOMDS6DG2YH5CYR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Streaming Deep Reinforcement Learning Finally Works","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"A. Rupam Mahmood, Gautham Vasan, Mohamed Elsayed","submitted_at":"2024-10-18T17:00:29Z","abstract_excerpt":"Natural intelligence processes experience as a continuous stream, sensing, acting, and learning moment-by-moment in real time. Streaming learning, the modus operandi of classic reinforcement learning (RL) algorithms like Q-learning and TD, mimics natural learning by using the most recent sample without storing it. This approach is also ideal for resource-constrained, communication-limited, and privacy-sensitive applications. However, in deep RL, learners almost always use batch updates and replay buffers, making them computationally expensive and incompatible with streaming learning. Although "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14606","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/2410.14606/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":"2026-07-05T09:45:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q4waMJ6DUwj9U8svUBRIrH8RQWkEfytHF0EItJUXZEN+me3vYTpi6YFZv46vW7z1KGTzb02s0yeVRVgIDZYmCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:14:24.463256Z"},"content_sha256":"996eaff28b9ef9453490864136eb7f91884eb379c12b0b0827a7491f8666c951","schema_version":"1.0","event_id":"sha256:996eaff28b9ef9453490864136eb7f91884eb379c12b0b0827a7491f8666c951"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SZHIKSAJQCQSOMDS6DG2YH5CYR/bundle.json","state_url":"https://pith.science/pith/SZHIKSAJQCQSOMDS6DG2YH5CYR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SZHIKSAJQCQSOMDS6DG2YH5CYR/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":"2026-08-10T02:14:24Z","links":{"resolver":"https://pith.science/pith/SZHIKSAJQCQSOMDS6DG2YH5CYR","bundle":"https://pith.science/pith/SZHIKSAJQCQSOMDS6DG2YH5CYR/bundle.json","state":"https://pith.science/pith/SZHIKSAJQCQSOMDS6DG2YH5CYR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SZHIKSAJQCQSOMDS6DG2YH5CYR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SZHIKSAJQCQSOMDS6DG2YH5CYR","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":"5a6cdda6afc66a7df532a0d4fa7565f8b9ccee7abff8bb55f64dbf08c3b75612","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-18T17:00:29Z","title_canon_sha256":"fc20dc22f847c194fcd1a7e68d65b3b8d96a2d8c4a6dc163b34ff05c26f3c2ea"},"schema_version":"1.0","source":{"id":"2410.14606","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14606","created_at":"2026-07-05T09:45:15Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14606v2","created_at":"2026-07-05T09:45:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14606","created_at":"2026-07-05T09:45:15Z"},{"alias_kind":"pith_short_12","alias_value":"SZHIKSAJQCQS","created_at":"2026-07-05T09:45:15Z"},{"alias_kind":"pith_short_16","alias_value":"SZHIKSAJQCQSOMDS","created_at":"2026-07-05T09:45:15Z"},{"alias_kind":"pith_short_8","alias_value":"SZHIKSAJ","created_at":"2026-07-05T09:45:15Z"}],"graph_snapshots":[{"event_id":"sha256:996eaff28b9ef9453490864136eb7f91884eb379c12b0b0827a7491f8666c951","target":"graph","created_at":"2026-07-05T09:45:15Z","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/2410.14606/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural intelligence processes experience as a continuous stream, sensing, acting, and learning moment-by-moment in real time. Streaming learning, the modus operandi of classic reinforcement learning (RL) algorithms like Q-learning and TD, mimics natural learning by using the most recent sample without storing it. This approach is also ideal for resource-constrained, communication-limited, and privacy-sensitive applications. However, in deep RL, learners almost always use batch updates and replay buffers, making them computationally expensive and incompatible with streaming learning. Although ","authors_text":"A. Rupam Mahmood, Gautham Vasan, Mohamed Elsayed","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-18T17:00:29Z","title":"Streaming Deep Reinforcement Learning Finally Works"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14606","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":"sha256:4707cb4fff618655198359cd7eaf920681729a53555fd8d5121bc657bbed085a","target":"record","created_at":"2026-07-05T09:45:15Z","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":"5a6cdda6afc66a7df532a0d4fa7565f8b9ccee7abff8bb55f64dbf08c3b75612","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-18T17:00:29Z","title_canon_sha256":"fc20dc22f847c194fcd1a7e68d65b3b8d96a2d8c4a6dc163b34ff05c26f3c2ea"},"schema_version":"1.0","source":{"id":"2410.14606","kind":"arxiv","version":2}},"canonical_sha256":"964e85480980a1273072f0cdac1fa2c4687fc6d57e75d1f51aadfed83c0797c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"964e85480980a1273072f0cdac1fa2c4687fc6d57e75d1f51aadfed83c0797c3","first_computed_at":"2026-07-05T09:45:15.518698Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:15.518698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ii7xeV69E2AgUP4et030WBigw/Xh7We/GiU56JTudP+to48qP71r5MA5bFC8mHjZRRBLjq9WVly02foNl6iJAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:15.519166Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.14606","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4707cb4fff618655198359cd7eaf920681729a53555fd8d5121bc657bbed085a","sha256:996eaff28b9ef9453490864136eb7f91884eb379c12b0b0827a7491f8666c951"],"state_sha256":"3b8ac8fa40e144af60b8198c81106f8d5c67735c46f15e33d599dd664546ce35"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"892Y4Idp60SjAhoUCu80JzTbz/bBIiZDw4g3pFVaFoehg80c3symFP0xE6ZL/My6QEl/YsE6FDClSfqeo6IZBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T02:14:24.467234Z","bundle_sha256":"706ae323b0d55fb9e0dc5256b81d1ee8fe1278e5669885f1d58f6d4c07f8a92e"}}