{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:M4H7WW5S3QEGPRPIEJDI7QX456","short_pith_number":"pith:M4H7WW5S","canonical_record":{"source":{"id":"2204.05437","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2022-04-11T23:10:42Z","cross_cats_sorted":[],"title_canon_sha256":"472c9f66065fe6c410078a321765256f0c92c6ba658f12da0db26f24036eb2de","abstract_canon_sha256":"2d1070621a31a0d36fe854f5c3918c3fe246c6483352ac4a54cd308a45540bed"},"schema_version":"1.0"},"canonical_sha256":"670ffb5bb2dc0867c5e822468fc2fcefbcf1acedcdf6ee7d97270c19cc4a2f8c","source":{"kind":"arxiv","id":"2204.05437","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.05437","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"arxiv_version","alias_value":"2204.05437v1","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05437","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"pith_short_12","alias_value":"M4H7WW5S3QEG","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"pith_short_16","alias_value":"M4H7WW5S3QEGPRPI","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"pith_short_8","alias_value":"M4H7WW5S","created_at":"2026-07-05T04:13:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:M4H7WW5S3QEGPRPIEJDI7QX456","target":"record","payload":{"canonical_record":{"source":{"id":"2204.05437","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2022-04-11T23:10:42Z","cross_cats_sorted":[],"title_canon_sha256":"472c9f66065fe6c410078a321765256f0c92c6ba658f12da0db26f24036eb2de","abstract_canon_sha256":"2d1070621a31a0d36fe854f5c3918c3fe246c6483352ac4a54cd308a45540bed"},"schema_version":"1.0"},"canonical_sha256":"670ffb5bb2dc0867c5e822468fc2fcefbcf1acedcdf6ee7d97270c19cc4a2f8c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:57.957573Z","signature_b64":"QBdMeuUl2/xalH/2R5uTWUWyrotPzG0DKfKjwme36jmoFLySRyFj9kWTkAxMOdDcxkL4eaZx9kQ/L8KO3waZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"670ffb5bb2dc0867c5e822468fc2fcefbcf1acedcdf6ee7d97270c19cc4a2f8c","last_reissued_at":"2026-07-05T04:13:57.957141Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:57.957141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.05437","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":"2026-07-05T04:13:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f2Rs/fWmB0WHaSwM9uT8Gw7ryT+cNWujC2trxd/eo8VyLOb2S6k2LnEKZ1t5jh9LPpuutbeihYTihNFhDRGeDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:36:37.837232Z"},"content_sha256":"c0dfdbeedd9db16b024e709f02e1cec7bce79dc37ceb7122453c5626e43362e7","schema_version":"1.0","event_id":"sha256:c0dfdbeedd9db16b024e709f02e1cec7bce79dc37ceb7122453c5626e43362e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:M4H7WW5S3QEGPRPIEJDI7QX456","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Implementing Online Reinforcement Learning with Temporal Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"James E. Smith","submitted_at":"2022-04-11T23:10:42Z","abstract_excerpt":"A Temporal Neural Network (TNN) architecture for implementing efficient online reinforcement learning is proposed and studied via simulation. The proposed T-learning system is composed of a frontend TNN that implements online unsupervised clustering and a backend TNN that implements online reinforcement learning. The reinforcement learning paradigm employs biologically plausible neo-Hebbian three-factor learning rules. As a working example, a prototype implementation of the cart-pole problem (balancing an inverted pendulum) is studied via simulation."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05437","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/2204.05437/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":"2026-07-05T04:13:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H53JC7PDSijaco/Ly5a7awCZbM/My/nYIFjvzFWvGv8KV0I9jUHyHUa8ir27H6N1aJncUR4Xv06n9Qti7c9uCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:36:37.837733Z"},"content_sha256":"80227114e1d17e3beb3b66fecc1d4c38a28d543659102d998c3fde52cf9809df","schema_version":"1.0","event_id":"sha256:80227114e1d17e3beb3b66fecc1d4c38a28d543659102d998c3fde52cf9809df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M4H7WW5S3QEGPRPIEJDI7QX456/bundle.json","state_url":"https://pith.science/pith/M4H7WW5S3QEGPRPIEJDI7QX456/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M4H7WW5S3QEGPRPIEJDI7QX456/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":"2026-08-15T23:36:37Z","links":{"resolver":"https://pith.science/pith/M4H7WW5S3QEGPRPIEJDI7QX456","bundle":"https://pith.science/pith/M4H7WW5S3QEGPRPIEJDI7QX456/bundle.json","state":"https://pith.science/pith/M4H7WW5S3QEGPRPIEJDI7QX456/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M4H7WW5S3QEGPRPIEJDI7QX456/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:M4H7WW5S3QEGPRPIEJDI7QX456","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":"2d1070621a31a0d36fe854f5c3918c3fe246c6483352ac4a54cd308a45540bed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2022-04-11T23:10:42Z","title_canon_sha256":"472c9f66065fe6c410078a321765256f0c92c6ba658f12da0db26f24036eb2de"},"schema_version":"1.0","source":{"id":"2204.05437","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.05437","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"arxiv_version","alias_value":"2204.05437v1","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05437","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"pith_short_12","alias_value":"M4H7WW5S3QEG","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"pith_short_16","alias_value":"M4H7WW5S3QEGPRPI","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"pith_short_8","alias_value":"M4H7WW5S","created_at":"2026-07-05T04:13:57Z"}],"graph_snapshots":[{"event_id":"sha256:80227114e1d17e3beb3b66fecc1d4c38a28d543659102d998c3fde52cf9809df","target":"graph","created_at":"2026-07-05T04:13:57Z","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/2204.05437/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A Temporal Neural Network (TNN) architecture for implementing efficient online reinforcement learning is proposed and studied via simulation. The proposed T-learning system is composed of a frontend TNN that implements online unsupervised clustering and a backend TNN that implements online reinforcement learning. The reinforcement learning paradigm employs biologically plausible neo-Hebbian three-factor learning rules. As a working example, a prototype implementation of the cart-pole problem (balancing an inverted pendulum) is studied via simulation.","authors_text":"James E. Smith","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2022-04-11T23:10:42Z","title":"Implementing Online Reinforcement Learning with Temporal Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05437","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:c0dfdbeedd9db16b024e709f02e1cec7bce79dc37ceb7122453c5626e43362e7","target":"record","created_at":"2026-07-05T04:13:57Z","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":"2d1070621a31a0d36fe854f5c3918c3fe246c6483352ac4a54cd308a45540bed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2022-04-11T23:10:42Z","title_canon_sha256":"472c9f66065fe6c410078a321765256f0c92c6ba658f12da0db26f24036eb2de"},"schema_version":"1.0","source":{"id":"2204.05437","kind":"arxiv","version":1}},"canonical_sha256":"670ffb5bb2dc0867c5e822468fc2fcefbcf1acedcdf6ee7d97270c19cc4a2f8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"670ffb5bb2dc0867c5e822468fc2fcefbcf1acedcdf6ee7d97270c19cc4a2f8c","first_computed_at":"2026-07-05T04:13:57.957141Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:13:57.957141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QBdMeuUl2/xalH/2R5uTWUWyrotPzG0DKfKjwme36jmoFLySRyFj9kWTkAxMOdDcxkL4eaZx9kQ/L8KO3waZAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:13:57.957573Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.05437","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0dfdbeedd9db16b024e709f02e1cec7bce79dc37ceb7122453c5626e43362e7","sha256:80227114e1d17e3beb3b66fecc1d4c38a28d543659102d998c3fde52cf9809df"],"state_sha256":"e6a8980e479f7ee9862ec1fe81593c9e3799f68e4940d92717c9d6d4330bcc6b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8jl1C0GrZNFYdd9HtJOVOPrGuIl2IL6VE0Vb627V3xsQS70PU3Xziz+oMMrheNvt34v0nU977EgMtjiSGhIfCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T23:36:37.842597Z","bundle_sha256":"99ce0ea4b0a0a7c00865b4f33cd161e2092a7d905ccc1eab9a8c5abb2c64cace"}}