{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IKWY6RDPNOWJQKKW2QNAW2XMT5","short_pith_number":"pith:IKWY6RDP","canonical_record":{"source":{"id":"2404.02235","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-02T18:45:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c3e9a8d4986c6fef3dbe7002dc03813e15b439858648dda5ee65a5ea5893e02f","abstract_canon_sha256":"da16e77ce4786e152e6db8de77f221a28eb9a2ab0434d2ab5c7be699e9b27775"},"schema_version":"1.0"},"canonical_sha256":"42ad8f446f6bac982956d41a0b6aec9f449e928ff0aefd1c8b4ba1109b1247f4","source":{"kind":"arxiv","id":"2404.02235","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.02235","created_at":"2026-07-05T08:03:52Z"},{"alias_kind":"arxiv_version","alias_value":"2404.02235v1","created_at":"2026-07-05T08:03:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02235","created_at":"2026-07-05T08:03:52Z"},{"alias_kind":"pith_short_12","alias_value":"IKWY6RDPNOWJ","created_at":"2026-07-05T08:03:52Z"},{"alias_kind":"pith_short_16","alias_value":"IKWY6RDPNOWJQKKW","created_at":"2026-07-05T08:03:52Z"},{"alias_kind":"pith_short_8","alias_value":"IKWY6RDP","created_at":"2026-07-05T08:03:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IKWY6RDPNOWJQKKW2QNAW2XMT5","target":"record","payload":{"canonical_record":{"source":{"id":"2404.02235","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-02T18:45:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c3e9a8d4986c6fef3dbe7002dc03813e15b439858648dda5ee65a5ea5893e02f","abstract_canon_sha256":"da16e77ce4786e152e6db8de77f221a28eb9a2ab0434d2ab5c7be699e9b27775"},"schema_version":"1.0"},"canonical_sha256":"42ad8f446f6bac982956d41a0b6aec9f449e928ff0aefd1c8b4ba1109b1247f4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:52.707995Z","signature_b64":"8ApICNAIat8qrM/Y8w2KkCtUW3d1EBXOGAZI/0nA28UGRKavlLFTvllemKpf1k31Wbdir2eyY6/y+kiN9upjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42ad8f446f6bac982956d41a0b6aec9f449e928ff0aefd1c8b4ba1109b1247f4","last_reissued_at":"2026-07-05T08:03:52.707559Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:52.707559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.02235","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":"2026-07-05T08:03:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"457ZJE0MZ7BftU5EAjOws0MzIwIb9fdvVAWTjifXw4qE/8O/i55frEhQydBjT0NHv4nUNU+YebnJyzlGgxMnDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:06:26.291442Z"},"content_sha256":"26fa4d361c417a9c576142fea32c5670f83cfe75722060250c1d244a7d4492fd","schema_version":"1.0","event_id":"sha256:26fa4d361c417a9c576142fea32c5670f83cfe75722060250c1d244a7d4492fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IKWY6RDPNOWJQKKW2QNAW2XMT5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is Exploration All You Need? Effective Exploration Characteristics for Transfer in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Geigh Zollicoffer, Jonathan C. Balloch, Julia Kim, Mark O. Riedl, Rishav Bhagat, Ruoran Jia","submitted_at":"2024-04-02T18:45:01Z","abstract_excerpt":"In deep reinforcement learning (RL) research, there has been a concerted effort to design more efficient and productive exploration methods while solving sparse-reward problems. These exploration methods often share common principles (e.g., improving diversity) and implementation details (e.g., intrinsic reward). Prior work found that non-stationary Markov decision processes (MDPs) require exploration to efficiently adapt to changes in the environment with online transfer learning. However, the relationship between specific exploration characteristics and effective transfer learning in deep RL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02235","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/2404.02235/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":"2026-07-05T08:03:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KhevDFbp91I+q6ySdyfmDRszhKZ9Xj/mzVX6AscUqe5dlC1/xOqh0v0dmeOdaVFU2SWrZiWzj49MrUQr89CMDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:06:26.291953Z"},"content_sha256":"c0ef49640c014127e1c3b264925604a5a48c3271d0a379c642e1e8076121f6ca","schema_version":"1.0","event_id":"sha256:c0ef49640c014127e1c3b264925604a5a48c3271d0a379c642e1e8076121f6ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IKWY6RDPNOWJQKKW2QNAW2XMT5/bundle.json","state_url":"https://pith.science/pith/IKWY6RDPNOWJQKKW2QNAW2XMT5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IKWY6RDPNOWJQKKW2QNAW2XMT5/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":"2026-08-09T13:06:26Z","links":{"resolver":"https://pith.science/pith/IKWY6RDPNOWJQKKW2QNAW2XMT5","bundle":"https://pith.science/pith/IKWY6RDPNOWJQKKW2QNAW2XMT5/bundle.json","state":"https://pith.science/pith/IKWY6RDPNOWJQKKW2QNAW2XMT5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IKWY6RDPNOWJQKKW2QNAW2XMT5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IKWY6RDPNOWJQKKW2QNAW2XMT5","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":"da16e77ce4786e152e6db8de77f221a28eb9a2ab0434d2ab5c7be699e9b27775","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-02T18:45:01Z","title_canon_sha256":"c3e9a8d4986c6fef3dbe7002dc03813e15b439858648dda5ee65a5ea5893e02f"},"schema_version":"1.0","source":{"id":"2404.02235","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.02235","created_at":"2026-07-05T08:03:52Z"},{"alias_kind":"arxiv_version","alias_value":"2404.02235v1","created_at":"2026-07-05T08:03:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02235","created_at":"2026-07-05T08:03:52Z"},{"alias_kind":"pith_short_12","alias_value":"IKWY6RDPNOWJ","created_at":"2026-07-05T08:03:52Z"},{"alias_kind":"pith_short_16","alias_value":"IKWY6RDPNOWJQKKW","created_at":"2026-07-05T08:03:52Z"},{"alias_kind":"pith_short_8","alias_value":"IKWY6RDP","created_at":"2026-07-05T08:03:52Z"}],"graph_snapshots":[{"event_id":"sha256:c0ef49640c014127e1c3b264925604a5a48c3271d0a379c642e1e8076121f6ca","target":"graph","created_at":"2026-07-05T08:03:52Z","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/2404.02235/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In deep reinforcement learning (RL) research, there has been a concerted effort to design more efficient and productive exploration methods while solving sparse-reward problems. These exploration methods often share common principles (e.g., improving diversity) and implementation details (e.g., intrinsic reward). Prior work found that non-stationary Markov decision processes (MDPs) require exploration to efficiently adapt to changes in the environment with online transfer learning. However, the relationship between specific exploration characteristics and effective transfer learning in deep RL","authors_text":"Geigh Zollicoffer, Jonathan C. Balloch, Julia Kim, Mark O. Riedl, Rishav Bhagat, Ruoran Jia","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-02T18:45:01Z","title":"Is Exploration All You Need? Effective Exploration Characteristics for Transfer in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02235","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":"sha256:26fa4d361c417a9c576142fea32c5670f83cfe75722060250c1d244a7d4492fd","target":"record","created_at":"2026-07-05T08:03:52Z","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":"da16e77ce4786e152e6db8de77f221a28eb9a2ab0434d2ab5c7be699e9b27775","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-02T18:45:01Z","title_canon_sha256":"c3e9a8d4986c6fef3dbe7002dc03813e15b439858648dda5ee65a5ea5893e02f"},"schema_version":"1.0","source":{"id":"2404.02235","kind":"arxiv","version":1}},"canonical_sha256":"42ad8f446f6bac982956d41a0b6aec9f449e928ff0aefd1c8b4ba1109b1247f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"42ad8f446f6bac982956d41a0b6aec9f449e928ff0aefd1c8b4ba1109b1247f4","first_computed_at":"2026-07-05T08:03:52.707559Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:52.707559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8ApICNAIat8qrM/Y8w2KkCtUW3d1EBXOGAZI/0nA28UGRKavlLFTvllemKpf1k31Wbdir2eyY6/y+kiN9upjBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:52.707995Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.02235","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26fa4d361c417a9c576142fea32c5670f83cfe75722060250c1d244a7d4492fd","sha256:c0ef49640c014127e1c3b264925604a5a48c3271d0a379c642e1e8076121f6ca"],"state_sha256":"f81dd5413a631a32a2ace03ccaedc20cd2dbe89b8043eba971e15aac4cdcdda3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IfzX8ANb1LDZ1rcMuqA3QdSNJGAnz9xBVnS1Yyr/9yhYMhMKvN+QkNecRSPtAio+5mbdYZfFjpcldI1VL74BDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:06:26.295265Z","bundle_sha256":"48baa2893abad75c3209c55314ab15a85ed5e7721542e042fcbaaf7432ceb5ff"}}