{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:PJRPF42HFQAU6QL5D42NXQ7DBB","short_pith_number":"pith:PJRPF42H","canonical_record":{"source":{"id":"2106.09776","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-17T19:33:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"072be103b6ba7e29fffec5e1b4319fc02571299feb5be8679034b56ace696033","abstract_canon_sha256":"e8bac2e4e34068b656a168b56f80083f99dcb140907461bb59296fba5fae4ab2"},"schema_version":"1.0"},"canonical_sha256":"7a62f2f3472c014f417d1f34dbc3e3087f97f70f048fedaaa75dcebb2f04df3e","source":{"kind":"arxiv","id":"2106.09776","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.09776","created_at":"2026-07-05T02:50:20Z"},{"alias_kind":"arxiv_version","alias_value":"2106.09776v1","created_at":"2026-07-05T02:50:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09776","created_at":"2026-07-05T02:50:20Z"},{"alias_kind":"pith_short_12","alias_value":"PJRPF42HFQAU","created_at":"2026-07-05T02:50:20Z"},{"alias_kind":"pith_short_16","alias_value":"PJRPF42HFQAU6QL5","created_at":"2026-07-05T02:50:20Z"},{"alias_kind":"pith_short_8","alias_value":"PJRPF42H","created_at":"2026-07-05T02:50:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:PJRPF42HFQAU6QL5D42NXQ7DBB","target":"record","payload":{"canonical_record":{"source":{"id":"2106.09776","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-17T19:33:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"072be103b6ba7e29fffec5e1b4319fc02571299feb5be8679034b56ace696033","abstract_canon_sha256":"e8bac2e4e34068b656a168b56f80083f99dcb140907461bb59296fba5fae4ab2"},"schema_version":"1.0"},"canonical_sha256":"7a62f2f3472c014f417d1f34dbc3e3087f97f70f048fedaaa75dcebb2f04df3e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:20.583342Z","signature_b64":"yYzuodmg/BWYHM516fYRbUnThPM6a/2mUNVEHPQfNW6OX/sElgjshZGvjL9X111/iqj1RVh8z0efS+TEEvFpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a62f2f3472c014f417d1f34dbc3e3087f97f70f048fedaaa75dcebb2f04df3e","last_reissued_at":"2026-07-05T02:50:20.582860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:20.582860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.09776","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":"2026-07-05T02:50:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j9GwY6fIWsH3FOelLkXsB45IXMgD5JMZdE9ZZxSoAOz5K6AB54RPzC61GNs5W9nXAC0E2EwvYfIUMLyYpp0DDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:27:32.076325Z"},"content_sha256":"eeb4b8a1d3845d0b361d4c6924ded4522b57b5cb9b6415d86eb97c11dc65c05b","schema_version":"1.0","event_id":"sha256:eeb4b8a1d3845d0b361d4c6924ded4522b57b5cb9b6415d86eb97c11dc65c05b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:PJRPF42HFQAU6QL5D42NXQ7DBB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adapting the Function Approximation Architecture in Online Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"John D. Martin, Joseph Modayil","submitted_at":"2021-06-17T19:33:26Z","abstract_excerpt":"The performance of a reinforcement learning (RL) system depends on the computational architecture used to approximate a value function. Deep learning methods provide both optimization techniques and architectures for approximating nonlinear functions from noisy, high-dimensional observations. However, prevailing optimization techniques are not designed for strictly-incremental online updates. Nor are standard architectures designed for observations with an a priori unknown structure: for example, light sensors randomly dispersed in space. This paper proposes an online RL prediction algorithm w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09776","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/2106.09776/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":"2026-07-05T02:50:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Kk3pT/T/2P3G+uzcIj1Zxcl43UriMSt+yEn3qmH+/Hp/YQlRcIHTUliuDSV1v9lya5rYz/1bi50/4nwO54dBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:27:32.076712Z"},"content_sha256":"9dab0aff7bedf348f9dc13b8e3086394d921255758521a10029073fdddd2bb8e","schema_version":"1.0","event_id":"sha256:9dab0aff7bedf348f9dc13b8e3086394d921255758521a10029073fdddd2bb8e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PJRPF42HFQAU6QL5D42NXQ7DBB/bundle.json","state_url":"https://pith.science/pith/PJRPF42HFQAU6QL5D42NXQ7DBB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PJRPF42HFQAU6QL5D42NXQ7DBB/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":"2026-08-11T21:27:32Z","links":{"resolver":"https://pith.science/pith/PJRPF42HFQAU6QL5D42NXQ7DBB","bundle":"https://pith.science/pith/PJRPF42HFQAU6QL5D42NXQ7DBB/bundle.json","state":"https://pith.science/pith/PJRPF42HFQAU6QL5D42NXQ7DBB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PJRPF42HFQAU6QL5D42NXQ7DBB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PJRPF42HFQAU6QL5D42NXQ7DBB","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":"e8bac2e4e34068b656a168b56f80083f99dcb140907461bb59296fba5fae4ab2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-17T19:33:26Z","title_canon_sha256":"072be103b6ba7e29fffec5e1b4319fc02571299feb5be8679034b56ace696033"},"schema_version":"1.0","source":{"id":"2106.09776","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.09776","created_at":"2026-07-05T02:50:20Z"},{"alias_kind":"arxiv_version","alias_value":"2106.09776v1","created_at":"2026-07-05T02:50:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09776","created_at":"2026-07-05T02:50:20Z"},{"alias_kind":"pith_short_12","alias_value":"PJRPF42HFQAU","created_at":"2026-07-05T02:50:20Z"},{"alias_kind":"pith_short_16","alias_value":"PJRPF42HFQAU6QL5","created_at":"2026-07-05T02:50:20Z"},{"alias_kind":"pith_short_8","alias_value":"PJRPF42H","created_at":"2026-07-05T02:50:20Z"}],"graph_snapshots":[{"event_id":"sha256:9dab0aff7bedf348f9dc13b8e3086394d921255758521a10029073fdddd2bb8e","target":"graph","created_at":"2026-07-05T02:50:20Z","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/2106.09776/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The performance of a reinforcement learning (RL) system depends on the computational architecture used to approximate a value function. Deep learning methods provide both optimization techniques and architectures for approximating nonlinear functions from noisy, high-dimensional observations. However, prevailing optimization techniques are not designed for strictly-incremental online updates. Nor are standard architectures designed for observations with an a priori unknown structure: for example, light sensors randomly dispersed in space. This paper proposes an online RL prediction algorithm w","authors_text":"John D. Martin, Joseph Modayil","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-17T19:33:26Z","title":"Adapting the Function Approximation Architecture in Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09776","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:eeb4b8a1d3845d0b361d4c6924ded4522b57b5cb9b6415d86eb97c11dc65c05b","target":"record","created_at":"2026-07-05T02:50:20Z","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":"e8bac2e4e34068b656a168b56f80083f99dcb140907461bb59296fba5fae4ab2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-17T19:33:26Z","title_canon_sha256":"072be103b6ba7e29fffec5e1b4319fc02571299feb5be8679034b56ace696033"},"schema_version":"1.0","source":{"id":"2106.09776","kind":"arxiv","version":1}},"canonical_sha256":"7a62f2f3472c014f417d1f34dbc3e3087f97f70f048fedaaa75dcebb2f04df3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a62f2f3472c014f417d1f34dbc3e3087f97f70f048fedaaa75dcebb2f04df3e","first_computed_at":"2026-07-05T02:50:20.582860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:50:20.582860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yYzuodmg/BWYHM516fYRbUnThPM6a/2mUNVEHPQfNW6OX/sElgjshZGvjL9X111/iqj1RVh8z0efS+TEEvFpDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:50:20.583342Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.09776","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eeb4b8a1d3845d0b361d4c6924ded4522b57b5cb9b6415d86eb97c11dc65c05b","sha256:9dab0aff7bedf348f9dc13b8e3086394d921255758521a10029073fdddd2bb8e"],"state_sha256":"0414a4b939746e0f4129f3738794fd00cba84be628e5ec7295d4c9871b6fa3a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N/Z9SYow7Lej2a6fzOJS8CLAr6aiogVtKv5kH2m9G+opAFaKsu5IFcYSiDPfbiP2ZrM8YB2eklryoIEjyMYZCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T21:27:32.079301Z","bundle_sha256":"ec37732bf858e2f6640b2307e90d13a348043af423bd00eb32a24891e5721bac"}}