{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6XKVO3SZ3O3BDTVKJK4JCYP3KX","short_pith_number":"pith:6XKVO3SZ","canonical_record":{"source":{"id":"2401.09750","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T06:32:53Z","cross_cats_sorted":[],"title_canon_sha256":"7dbc59350deb07aa61af3e02f982813fbd2fd5a55babf78e47914fd20bc8c5cd","abstract_canon_sha256":"b168219034de6d00fab261eaeb10071343514a7f1944404b6d59b6e227315ac3"},"schema_version":"1.0"},"canonical_sha256":"f5d5576e59dbb611ceaa4ab89161fb55ccf73b24819334ee15231101eaa5d154","source":{"kind":"arxiv","id":"2401.09750","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.09750","created_at":"2026-07-05T08:20:27Z"},{"alias_kind":"arxiv_version","alias_value":"2401.09750v4","created_at":"2026-07-05T08:20:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09750","created_at":"2026-07-05T08:20:27Z"},{"alias_kind":"pith_short_12","alias_value":"6XKVO3SZ3O3B","created_at":"2026-07-05T08:20:27Z"},{"alias_kind":"pith_short_16","alias_value":"6XKVO3SZ3O3BDTVK","created_at":"2026-07-05T08:20:27Z"},{"alias_kind":"pith_short_8","alias_value":"6XKVO3SZ","created_at":"2026-07-05T08:20:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6XKVO3SZ3O3BDTVKJK4JCYP3KX","target":"record","payload":{"canonical_record":{"source":{"id":"2401.09750","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T06:32:53Z","cross_cats_sorted":[],"title_canon_sha256":"7dbc59350deb07aa61af3e02f982813fbd2fd5a55babf78e47914fd20bc8c5cd","abstract_canon_sha256":"b168219034de6d00fab261eaeb10071343514a7f1944404b6d59b6e227315ac3"},"schema_version":"1.0"},"canonical_sha256":"f5d5576e59dbb611ceaa4ab89161fb55ccf73b24819334ee15231101eaa5d154","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:27.152469Z","signature_b64":"Dav147gO10vdMcu2VSm8M9WtzyjckBm+js8Ac8gR3BKSsI/jwPNYOKq2iAWu1BCOgVD+90bYf6lotcgKB4VSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5d5576e59dbb611ceaa4ab89161fb55ccf73b24819334ee15231101eaa5d154","last_reissued_at":"2026-07-05T08:20:27.152008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:27.152008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.09750","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:20:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5OTLIexnqa9XoB7h8jocvpzmY0IbpsjgN1BceDL1Dt8whfOMkXgeF6hbKZGRGJwWkY9xQbDD3kJeUbsNCz8RDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:27:06.720415Z"},"content_sha256":"449330057d0eff72a6fb3e7ae062c15c6541e14b001f40af66fc69b542266fb2","schema_version":"1.0","event_id":"sha256:449330057d0eff72a6fb3e7ae062c15c6541e14b001f40af66fc69b542266fb2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6XKVO3SZ3O3BDTVKJK4JCYP3KX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploration and Anti-Exploration with Distributional Random Network Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiafei Lyu, Jian Tao, Kai Yang, Xiu Li","submitted_at":"2024-01-18T06:32:53Z","abstract_excerpt":"Exploration remains a critical issue in deep reinforcement learning for an agent to attain high returns in unknown environments. Although the prevailing exploration Random Network Distillation (RND) algorithm has been demonstrated to be effective in numerous environments, it often needs more discriminative power in bonus allocation. This paper highlights the \"bonus inconsistency\" issue within RND, pinpointing its primary limitation. To address this issue, we introduce the Distributional RND (DRND), a derivative of the RND. DRND enhances the exploration process by distilling a distribution of r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09750","kind":"arxiv","version":4},"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/2401.09750/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":"2026-07-05T08:20:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I8fwxEt1/Kacq74LUUkQTaFV1OtgDRRzy7nl+RJ8l1mBsBWCrOa+I47XhDOXWlqzO2RNdWBmWn45taoSaVXkCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:27:06.720793Z"},"content_sha256":"258dfa5ac73f4175092a4570561039d2f628d4ba5fc34af4cfd9cde15229b7c5","schema_version":"1.0","event_id":"sha256:258dfa5ac73f4175092a4570561039d2f628d4ba5fc34af4cfd9cde15229b7c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6XKVO3SZ3O3BDTVKJK4JCYP3KX/bundle.json","state_url":"https://pith.science/pith/6XKVO3SZ3O3BDTVKJK4JCYP3KX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6XKVO3SZ3O3BDTVKJK4JCYP3KX/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":"2026-08-14T18:27:06Z","links":{"resolver":"https://pith.science/pith/6XKVO3SZ3O3BDTVKJK4JCYP3KX","bundle":"https://pith.science/pith/6XKVO3SZ3O3BDTVKJK4JCYP3KX/bundle.json","state":"https://pith.science/pith/6XKVO3SZ3O3BDTVKJK4JCYP3KX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6XKVO3SZ3O3BDTVKJK4JCYP3KX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6XKVO3SZ3O3BDTVKJK4JCYP3KX","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":"b168219034de6d00fab261eaeb10071343514a7f1944404b6d59b6e227315ac3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T06:32:53Z","title_canon_sha256":"7dbc59350deb07aa61af3e02f982813fbd2fd5a55babf78e47914fd20bc8c5cd"},"schema_version":"1.0","source":{"id":"2401.09750","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.09750","created_at":"2026-07-05T08:20:27Z"},{"alias_kind":"arxiv_version","alias_value":"2401.09750v4","created_at":"2026-07-05T08:20:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09750","created_at":"2026-07-05T08:20:27Z"},{"alias_kind":"pith_short_12","alias_value":"6XKVO3SZ3O3B","created_at":"2026-07-05T08:20:27Z"},{"alias_kind":"pith_short_16","alias_value":"6XKVO3SZ3O3BDTVK","created_at":"2026-07-05T08:20:27Z"},{"alias_kind":"pith_short_8","alias_value":"6XKVO3SZ","created_at":"2026-07-05T08:20:27Z"}],"graph_snapshots":[{"event_id":"sha256:258dfa5ac73f4175092a4570561039d2f628d4ba5fc34af4cfd9cde15229b7c5","target":"graph","created_at":"2026-07-05T08:20:27Z","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/2401.09750/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exploration remains a critical issue in deep reinforcement learning for an agent to attain high returns in unknown environments. Although the prevailing exploration Random Network Distillation (RND) algorithm has been demonstrated to be effective in numerous environments, it often needs more discriminative power in bonus allocation. This paper highlights the \"bonus inconsistency\" issue within RND, pinpointing its primary limitation. To address this issue, we introduce the Distributional RND (DRND), a derivative of the RND. DRND enhances the exploration process by distilling a distribution of r","authors_text":"Jiafei Lyu, Jian Tao, Kai Yang, Xiu Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T06:32:53Z","title":"Exploration and Anti-Exploration with Distributional Random Network Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09750","kind":"arxiv","version":4},"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":"sha256:449330057d0eff72a6fb3e7ae062c15c6541e14b001f40af66fc69b542266fb2","target":"record","created_at":"2026-07-05T08:20:27Z","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":"b168219034de6d00fab261eaeb10071343514a7f1944404b6d59b6e227315ac3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T06:32:53Z","title_canon_sha256":"7dbc59350deb07aa61af3e02f982813fbd2fd5a55babf78e47914fd20bc8c5cd"},"schema_version":"1.0","source":{"id":"2401.09750","kind":"arxiv","version":4}},"canonical_sha256":"f5d5576e59dbb611ceaa4ab89161fb55ccf73b24819334ee15231101eaa5d154","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5d5576e59dbb611ceaa4ab89161fb55ccf73b24819334ee15231101eaa5d154","first_computed_at":"2026-07-05T08:20:27.152008Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:20:27.152008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dav147gO10vdMcu2VSm8M9WtzyjckBm+js8Ac8gR3BKSsI/jwPNYOKq2iAWu1BCOgVD+90bYf6lotcgKB4VSBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:20:27.152469Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.09750","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:449330057d0eff72a6fb3e7ae062c15c6541e14b001f40af66fc69b542266fb2","sha256:258dfa5ac73f4175092a4570561039d2f628d4ba5fc34af4cfd9cde15229b7c5"],"state_sha256":"ef3a09a8d312972027b1f08061c56a00ffd6d039151c40c6593e377abe5404d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TU/enNEJfTvPrGUdrUuShCxiVuVWwi/EJ+3zBC1fnjQBi0POzo5e2UMOlYFr5yJva5nkiHv/fQ00kA+3ceKMDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T18:27:06.724261Z","bundle_sha256":"4c2c6baa5954420b6750d2baeb6864d79e68d36f18c285b60586cc7e2ca9a33a"}}