{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DHKULPDTCVBX5B6F4WLQF3PXLR","short_pith_number":"pith:DHKULPDT","canonical_record":{"source":{"id":"2302.10825","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-02-21T17:00:05Z","cross_cats_sorted":[],"title_canon_sha256":"43b7ce746ba6a7a0000eefd5def493b3bc1f090d792a6bb18f905570e4cb8be9","abstract_canon_sha256":"a375d90d39a209d8b7fefe239d3b454bb3ab9d34cd6a4867b7ac004e791d4fb7"},"schema_version":"1.0"},"canonical_sha256":"19d545bc7315437e87c5e59702edf75c7e29d9479d6a69f5c16815bfd076dd58","source":{"kind":"arxiv","id":"2302.10825","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.10825","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"arxiv_version","alias_value":"2302.10825v1","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10825","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"pith_short_12","alias_value":"DHKULPDTCVBX","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"pith_short_16","alias_value":"DHKULPDTCVBX5B6F","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"pith_short_8","alias_value":"DHKULPDT","created_at":"2026-07-05T05:44:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DHKULPDTCVBX5B6F4WLQF3PXLR","target":"record","payload":{"canonical_record":{"source":{"id":"2302.10825","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-02-21T17:00:05Z","cross_cats_sorted":[],"title_canon_sha256":"43b7ce746ba6a7a0000eefd5def493b3bc1f090d792a6bb18f905570e4cb8be9","abstract_canon_sha256":"a375d90d39a209d8b7fefe239d3b454bb3ab9d34cd6a4867b7ac004e791d4fb7"},"schema_version":"1.0"},"canonical_sha256":"19d545bc7315437e87c5e59702edf75c7e29d9479d6a69f5c16815bfd076dd58","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:44:22.389286Z","signature_b64":"f7vHl2Hd0eOwuFLMSl17rb4M/O0Ij+3RLC5dVKof29icFwONzpqxPJQmS5/Q75vBXKbXi8M6YKIiDdSzcDX+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19d545bc7315437e87c5e59702edf75c7e29d9479d6a69f5c16815bfd076dd58","last_reissued_at":"2026-07-05T05:44:22.388894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:44:22.388894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.10825","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":"2026-07-05T05:44:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sr3mU6nd4HOSKoYRffMo6Ejcaht80LOQ/xcJbEoWx/d14srF/fJVgaq4UiXhxgP1kW2+bg7ukpGi+aJTk9c5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:07:38.124223Z"},"content_sha256":"8afe390879b03ed8935ed6cfc6bf4ab8177fb2d1e73f7388f5c8813d63a84d3b","schema_version":"1.0","event_id":"sha256:8afe390879b03ed8935ed6cfc6bf4ab8177fb2d1e73f7388f5c8813d63a84d3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DHKULPDTCVBX5B6F4WLQF3PXLR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Curiosity-driven Exploration in Sparse-reward Multi-agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiong Li, Pratik Gajane","submitted_at":"2023-02-21T17:00:05Z","abstract_excerpt":"Sparsity of rewards while applying a deep reinforcement learning method negatively affects its sample-efficiency. A viable solution to deal with the sparsity of rewards is to learn via intrinsic motivation which advocates for adding an intrinsic reward to the reward function to encourage the agent to explore the environment and expand the sample space. Though intrinsic motivation methods are widely used to improve data-efficient learning in the reinforcement learning model, they also suffer from the so-called detachment problem. In this article, we discuss the limitations of intrinsic curiosit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10825","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/2302.10825/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":"2026-07-05T05:44:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4TKpJLi1M9aTa8ODRsqQNqSI/N5W/34W7F52p9NPt27ImPlZphkwKBln14d/8DHQcHit7hzcYTZzuTzboKkTAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:07:38.124592Z"},"content_sha256":"cd752ea70a1e8f951f28b4fab9c98d88d3360ca60b9cef301f3e84f56b72a486","schema_version":"1.0","event_id":"sha256:cd752ea70a1e8f951f28b4fab9c98d88d3360ca60b9cef301f3e84f56b72a486"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DHKULPDTCVBX5B6F4WLQF3PXLR/bundle.json","state_url":"https://pith.science/pith/DHKULPDTCVBX5B6F4WLQF3PXLR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DHKULPDTCVBX5B6F4WLQF3PXLR/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":"2026-08-18T09:07:38Z","links":{"resolver":"https://pith.science/pith/DHKULPDTCVBX5B6F4WLQF3PXLR","bundle":"https://pith.science/pith/DHKULPDTCVBX5B6F4WLQF3PXLR/bundle.json","state":"https://pith.science/pith/DHKULPDTCVBX5B6F4WLQF3PXLR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DHKULPDTCVBX5B6F4WLQF3PXLR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DHKULPDTCVBX5B6F4WLQF3PXLR","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":"a375d90d39a209d8b7fefe239d3b454bb3ab9d34cd6a4867b7ac004e791d4fb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-02-21T17:00:05Z","title_canon_sha256":"43b7ce746ba6a7a0000eefd5def493b3bc1f090d792a6bb18f905570e4cb8be9"},"schema_version":"1.0","source":{"id":"2302.10825","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.10825","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"arxiv_version","alias_value":"2302.10825v1","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10825","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"pith_short_12","alias_value":"DHKULPDTCVBX","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"pith_short_16","alias_value":"DHKULPDTCVBX5B6F","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"pith_short_8","alias_value":"DHKULPDT","created_at":"2026-07-05T05:44:22Z"}],"graph_snapshots":[{"event_id":"sha256:cd752ea70a1e8f951f28b4fab9c98d88d3360ca60b9cef301f3e84f56b72a486","target":"graph","created_at":"2026-07-05T05:44:22Z","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/2302.10825/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparsity of rewards while applying a deep reinforcement learning method negatively affects its sample-efficiency. A viable solution to deal with the sparsity of rewards is to learn via intrinsic motivation which advocates for adding an intrinsic reward to the reward function to encourage the agent to explore the environment and expand the sample space. Though intrinsic motivation methods are widely used to improve data-efficient learning in the reinforcement learning model, they also suffer from the so-called detachment problem. In this article, we discuss the limitations of intrinsic curiosit","authors_text":"Jiong Li, Pratik Gajane","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-02-21T17:00:05Z","title":"Curiosity-driven Exploration in Sparse-reward Multi-agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10825","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":"sha256:8afe390879b03ed8935ed6cfc6bf4ab8177fb2d1e73f7388f5c8813d63a84d3b","target":"record","created_at":"2026-07-05T05:44:22Z","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":"a375d90d39a209d8b7fefe239d3b454bb3ab9d34cd6a4867b7ac004e791d4fb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-02-21T17:00:05Z","title_canon_sha256":"43b7ce746ba6a7a0000eefd5def493b3bc1f090d792a6bb18f905570e4cb8be9"},"schema_version":"1.0","source":{"id":"2302.10825","kind":"arxiv","version":1}},"canonical_sha256":"19d545bc7315437e87c5e59702edf75c7e29d9479d6a69f5c16815bfd076dd58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19d545bc7315437e87c5e59702edf75c7e29d9479d6a69f5c16815bfd076dd58","first_computed_at":"2026-07-05T05:44:22.388894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:44:22.388894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f7vHl2Hd0eOwuFLMSl17rb4M/O0Ij+3RLC5dVKof29icFwONzpqxPJQmS5/Q75vBXKbXi8M6YKIiDdSzcDX+Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:44:22.389286Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.10825","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8afe390879b03ed8935ed6cfc6bf4ab8177fb2d1e73f7388f5c8813d63a84d3b","sha256:cd752ea70a1e8f951f28b4fab9c98d88d3360ca60b9cef301f3e84f56b72a486"],"state_sha256":"46a669cd0dfd68fdf909810ffc8225e84388245a67253faecbc31438e981c277"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fETczwS1PZ11b2OMGEyZL0v9n29mpH8pVEhHsH3q5H6aDRSMvwOOJ7bzmKMBPHDuh/a+oXiB6ct++BA8Kh7PBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T09:07:38.126995Z","bundle_sha256":"94843de65b5cb9711b8708aafa45fa7945827e411c5e1cbeae9bcbc368aac756"}}