{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FTEXI7L3PVM2ZPO7RCSQYIO7VH","short_pith_number":"pith:FTEXI7L3","canonical_record":{"source":{"id":"2306.16021","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-28T08:48:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a551f734ee63eff8c48df69f1ce15adf4e96dd7f1cfe3f6514e37c17f244484e","abstract_canon_sha256":"e7a7a136b79ef5813c97fd9522b205db06a3ede36f245796d8634315e93047ad"},"schema_version":"1.0"},"canonical_sha256":"2cc9747d7b7d59acbddf88a50c21dfa9f36947e22ded4059c19b74e1f962f16c","source":{"kind":"arxiv","id":"2306.16021","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.16021","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"2306.16021v3","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16021","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"FTEXI7L3PVM2","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"pith_short_16","alias_value":"FTEXI7L3PVM2ZPO7","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"pith_short_8","alias_value":"FTEXI7L3","created_at":"2026-07-05T08:11:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FTEXI7L3PVM2ZPO7RCSQYIO7VH","target":"record","payload":{"canonical_record":{"source":{"id":"2306.16021","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-28T08:48:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a551f734ee63eff8c48df69f1ce15adf4e96dd7f1cfe3f6514e37c17f244484e","abstract_canon_sha256":"e7a7a136b79ef5813c97fd9522b205db06a3ede36f245796d8634315e93047ad"},"schema_version":"1.0"},"canonical_sha256":"2cc9747d7b7d59acbddf88a50c21dfa9f36947e22ded4059c19b74e1f962f16c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:53.285553Z","signature_b64":"P22RSglMUFCslMSvcNiH5Y9YNndz46wuKuuuMSO3wro3Zno7wIrR/Wp30k97X+8fiGr745QEn7nu9qXDU6c0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cc9747d7b7d59acbddf88a50c21dfa9f36947e22ded4059c19b74e1f962f16c","last_reissued_at":"2026-07-05T08:11:53.285155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:53.285155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.16021","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:11:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wsCHBFpiqoolhWYXtb9O8UOi9XRXTdkVk30Ro2R5Yjaqjiql5k0hB4zsQD0HQ/aZEbuC/B1/QndA1L6/mtNxBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T20:23:29.425368Z"},"content_sha256":"7af051113c75ebae784542a5cec43d145327164d98bb7d770fb63e62aca5acfa","schema_version":"1.0","event_id":"sha256:7af051113c75ebae784542a5cec43d145327164d98bb7d770fb63e62aca5acfa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FTEXI7L3PVM2ZPO7RCSQYIO7VH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aditya Mohan, Amy Zhang, Marius Lindauer","submitted_at":"2023-06-28T08:48:40Z","abstract_excerpt":"Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural Networks (DNNs) for function approximation, has demonstrated considerable success in numerous applications. However, its practicality in addressing various real-world scenarios, characterized by diverse and unpredictable dynamics, noisy signals, and large state and action spaces, remains limited. This limitation stems from poor data efficiency, limited generalization capabilities, a lack of safety guarantees, and the absence of interpretability, among other factors. To overcome these challenges and improve per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.16021","kind":"arxiv","version":3},"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/2306.16021/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":"2026-07-05T08:11:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D6YcfoOZfbkey9HRkmR+RkWdJvFCt8Qw7HmjK0UI7mwk4gg3S8k4BE7z+jVLkk8XUfvKW+HFieBBA9SXQOuGBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T20:23:29.425757Z"},"content_sha256":"025ed79f4ad60fc2f20004176a6e85c4f2a9a22250f564ffd4c516bd57b851b0","schema_version":"1.0","event_id":"sha256:025ed79f4ad60fc2f20004176a6e85c4f2a9a22250f564ffd4c516bd57b851b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FTEXI7L3PVM2ZPO7RCSQYIO7VH/bundle.json","state_url":"https://pith.science/pith/FTEXI7L3PVM2ZPO7RCSQYIO7VH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FTEXI7L3PVM2ZPO7RCSQYIO7VH/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":"2026-07-08T20:23:29Z","links":{"resolver":"https://pith.science/pith/FTEXI7L3PVM2ZPO7RCSQYIO7VH","bundle":"https://pith.science/pith/FTEXI7L3PVM2ZPO7RCSQYIO7VH/bundle.json","state":"https://pith.science/pith/FTEXI7L3PVM2ZPO7RCSQYIO7VH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FTEXI7L3PVM2ZPO7RCSQYIO7VH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FTEXI7L3PVM2ZPO7RCSQYIO7VH","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":"e7a7a136b79ef5813c97fd9522b205db06a3ede36f245796d8634315e93047ad","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-28T08:48:40Z","title_canon_sha256":"a551f734ee63eff8c48df69f1ce15adf4e96dd7f1cfe3f6514e37c17f244484e"},"schema_version":"1.0","source":{"id":"2306.16021","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.16021","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"2306.16021v3","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16021","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"FTEXI7L3PVM2","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"pith_short_16","alias_value":"FTEXI7L3PVM2ZPO7","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"pith_short_8","alias_value":"FTEXI7L3","created_at":"2026-07-05T08:11:53Z"}],"graph_snapshots":[{"event_id":"sha256:025ed79f4ad60fc2f20004176a6e85c4f2a9a22250f564ffd4c516bd57b851b0","target":"graph","created_at":"2026-07-05T08:11:53Z","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/2306.16021/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural Networks (DNNs) for function approximation, has demonstrated considerable success in numerous applications. However, its practicality in addressing various real-world scenarios, characterized by diverse and unpredictable dynamics, noisy signals, and large state and action spaces, remains limited. This limitation stems from poor data efficiency, limited generalization capabilities, a lack of safety guarantees, and the absence of interpretability, among other factors. To overcome these challenges and improve per","authors_text":"Aditya Mohan, Amy Zhang, Marius Lindauer","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-28T08:48:40Z","title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.16021","kind":"arxiv","version":3},"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":"sha256:7af051113c75ebae784542a5cec43d145327164d98bb7d770fb63e62aca5acfa","target":"record","created_at":"2026-07-05T08:11:53Z","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":"e7a7a136b79ef5813c97fd9522b205db06a3ede36f245796d8634315e93047ad","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-28T08:48:40Z","title_canon_sha256":"a551f734ee63eff8c48df69f1ce15adf4e96dd7f1cfe3f6514e37c17f244484e"},"schema_version":"1.0","source":{"id":"2306.16021","kind":"arxiv","version":3}},"canonical_sha256":"2cc9747d7b7d59acbddf88a50c21dfa9f36947e22ded4059c19b74e1f962f16c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cc9747d7b7d59acbddf88a50c21dfa9f36947e22ded4059c19b74e1f962f16c","first_computed_at":"2026-07-05T08:11:53.285155Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:11:53.285155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P22RSglMUFCslMSvcNiH5Y9YNndz46wuKuuuMSO3wro3Zno7wIrR/Wp30k97X+8fiGr745QEn7nu9qXDU6c0AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:11:53.285553Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.16021","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7af051113c75ebae784542a5cec43d145327164d98bb7d770fb63e62aca5acfa","sha256:025ed79f4ad60fc2f20004176a6e85c4f2a9a22250f564ffd4c516bd57b851b0"],"state_sha256":"d01a05d684ccebc2e70d984347c101225bfd6fb6dea7f245b6a99bac51a601b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T0zdh+qeUErlGYoWTdW0jAOyaNJb/7W+l0fe9SWYA+/49s6vPnungpmZcd9HaPnJPtV10yuM87LwSHQx4RYxDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T20:23:29.428445Z","bundle_sha256":"e9ea40aabc40eb4d65d417c4f3e7b9811a0d83369ea8f60ef94006def7725be8"}}