{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CRM3VLRO5NRJOT7XKQPQ5WP77E","short_pith_number":"pith:CRM3VLRO","canonical_record":{"source":{"id":"2411.13410","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T15:52:03Z","cross_cats_sorted":[],"title_canon_sha256":"4b9b01cf59c28f008378bf5d8916994738beede4cfb97f4edd077f5a6163b8f9","abstract_canon_sha256":"b10c1b452f192bc7de05e0f66d28a6a0f1b7eb665fe4e05161e6cc09977a7f53"},"schema_version":"1.0"},"canonical_sha256":"1459baae2eeb62974ff7541f0ed9fff93ab6a101e0bcdd1e82ea06ac3e74d97f","source":{"kind":"arxiv","id":"2411.13410","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13410","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13410v1","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13410","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"pith_short_12","alias_value":"CRM3VLRO5NRJ","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"pith_short_16","alias_value":"CRM3VLRO5NRJOT7X","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"pith_short_8","alias_value":"CRM3VLRO","created_at":"2026-07-05T09:38:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CRM3VLRO5NRJOT7XKQPQ5WP77E","target":"record","payload":{"canonical_record":{"source":{"id":"2411.13410","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T15:52:03Z","cross_cats_sorted":[],"title_canon_sha256":"4b9b01cf59c28f008378bf5d8916994738beede4cfb97f4edd077f5a6163b8f9","abstract_canon_sha256":"b10c1b452f192bc7de05e0f66d28a6a0f1b7eb665fe4e05161e6cc09977a7f53"},"schema_version":"1.0"},"canonical_sha256":"1459baae2eeb62974ff7541f0ed9fff93ab6a101e0bcdd1e82ea06ac3e74d97f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:16.565094Z","signature_b64":"NCI7emskLJbWjB3eOS+MGLsGQHp9BrTDjQSdHw4tGa3peQ38tLiwYAwGSwPcjXrexFyfW11/l6V24RDxW8QmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1459baae2eeb62974ff7541f0ed9fff93ab6a101e0bcdd1e82ea06ac3e74d97f","last_reissued_at":"2026-07-05T09:38:16.564653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:16.564653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.13410","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":"2026-07-05T09:38:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HO6tzqRBccOWFHX3N/bPqBTdVBHz4XzrXk4PHnnx+Gp+wueP0xkd5vb8sG+3WCW0Mrc5t2GdVn+rISBxouR5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:58:49.262317Z"},"content_sha256":"73a11c9ab1c44f8130db7ed14db689bab57f321a3ca158737c3c5a3293559051","schema_version":"1.0","event_id":"sha256:73a11c9ab1c44f8130db7ed14db689bab57f321a3ca158737c3c5a3293559051"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CRM3VLRO5NRJOT7XKQPQ5WP77E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey On Enhancing Reinforcement Learning in Complex Environments: Insights from Human and LLM Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alireza Rashidi Laleh, Majid Nili Ahmadabadi","submitted_at":"2024-11-20T15:52:03Z","abstract_excerpt":"Reinforcement learning (RL) is one of the active fields in machine learning, demonstrating remarkable potential in tackling real-world challenges. Despite its promising prospects, this methodology has encountered with issues and challenges, hindering it from achieving the best performance. In particular, these approaches lack decent performance when navigating environments and solving tasks with large observation space, often resulting in sample-inefficiency and prolonged learning times. This issue, commonly referred to as the curse of dimensionality, complicates decision-making for RL agents,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13410","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/2411.13410/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":"2026-07-05T09:38:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"73YkYVhzxtSeAAYq7Jcvro18yYf0nBGhKEabuoZArMIW1pG2bkfc6EkZovH2s7t/6P+xs+E3QGYTbktzJ+TaCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:58:49.262833Z"},"content_sha256":"98468c5ff1e44393bfb898b8f8a6430d064a3fd3296caa4a5e5887d4e4ba3849","schema_version":"1.0","event_id":"sha256:98468c5ff1e44393bfb898b8f8a6430d064a3fd3296caa4a5e5887d4e4ba3849"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CRM3VLRO5NRJOT7XKQPQ5WP77E/bundle.json","state_url":"https://pith.science/pith/CRM3VLRO5NRJOT7XKQPQ5WP77E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CRM3VLRO5NRJOT7XKQPQ5WP77E/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":"2026-08-10T04:58:49Z","links":{"resolver":"https://pith.science/pith/CRM3VLRO5NRJOT7XKQPQ5WP77E","bundle":"https://pith.science/pith/CRM3VLRO5NRJOT7XKQPQ5WP77E/bundle.json","state":"https://pith.science/pith/CRM3VLRO5NRJOT7XKQPQ5WP77E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CRM3VLRO5NRJOT7XKQPQ5WP77E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CRM3VLRO5NRJOT7XKQPQ5WP77E","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":"b10c1b452f192bc7de05e0f66d28a6a0f1b7eb665fe4e05161e6cc09977a7f53","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T15:52:03Z","title_canon_sha256":"4b9b01cf59c28f008378bf5d8916994738beede4cfb97f4edd077f5a6163b8f9"},"schema_version":"1.0","source":{"id":"2411.13410","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13410","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13410v1","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13410","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"pith_short_12","alias_value":"CRM3VLRO5NRJ","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"pith_short_16","alias_value":"CRM3VLRO5NRJOT7X","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"pith_short_8","alias_value":"CRM3VLRO","created_at":"2026-07-05T09:38:16Z"}],"graph_snapshots":[{"event_id":"sha256:98468c5ff1e44393bfb898b8f8a6430d064a3fd3296caa4a5e5887d4e4ba3849","target":"graph","created_at":"2026-07-05T09:38:16Z","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/2411.13410/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is one of the active fields in machine learning, demonstrating remarkable potential in tackling real-world challenges. Despite its promising prospects, this methodology has encountered with issues and challenges, hindering it from achieving the best performance. In particular, these approaches lack decent performance when navigating environments and solving tasks with large observation space, often resulting in sample-inefficiency and prolonged learning times. This issue, commonly referred to as the curse of dimensionality, complicates decision-making for RL agents,","authors_text":"Alireza Rashidi Laleh, Majid Nili Ahmadabadi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T15:52:03Z","title":"A Survey On Enhancing Reinforcement Learning in Complex Environments: Insights from Human and LLM Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13410","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":"sha256:73a11c9ab1c44f8130db7ed14db689bab57f321a3ca158737c3c5a3293559051","target":"record","created_at":"2026-07-05T09:38:16Z","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":"b10c1b452f192bc7de05e0f66d28a6a0f1b7eb665fe4e05161e6cc09977a7f53","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T15:52:03Z","title_canon_sha256":"4b9b01cf59c28f008378bf5d8916994738beede4cfb97f4edd077f5a6163b8f9"},"schema_version":"1.0","source":{"id":"2411.13410","kind":"arxiv","version":1}},"canonical_sha256":"1459baae2eeb62974ff7541f0ed9fff93ab6a101e0bcdd1e82ea06ac3e74d97f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1459baae2eeb62974ff7541f0ed9fff93ab6a101e0bcdd1e82ea06ac3e74d97f","first_computed_at":"2026-07-05T09:38:16.564653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:16.564653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NCI7emskLJbWjB3eOS+MGLsGQHp9BrTDjQSdHw4tGa3peQ38tLiwYAwGSwPcjXrexFyfW11/l6V24RDxW8QmAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:16.565094Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.13410","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73a11c9ab1c44f8130db7ed14db689bab57f321a3ca158737c3c5a3293559051","sha256:98468c5ff1e44393bfb898b8f8a6430d064a3fd3296caa4a5e5887d4e4ba3849"],"state_sha256":"c04d077fdb255db46ff332ee5ab21ba80b2512c052cfaaf4fa75c7462f3067ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rfZQikSBRUaKn/63rpWeoi/4zzbvZwUD47G+ZestGWDA3KreGdqTjMv/uZbodUppKXoa7rlUkoZZEdw+7QmEDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T04:58:49.268629Z","bundle_sha256":"bc4d934d33e24d0933d36539a8bb0088234709aaa7ebed747905ad41034872e4"}}