{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZXDDSBVZFDXM4DBZIFXYVL2XPT","short_pith_number":"pith:ZXDDSBVZ","canonical_record":{"source":{"id":"2103.07084","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2021-03-12T04:54:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"64fed99cc90007a0fa1d453ae76a03842b4a172ba9d0f408635f15d4d2ecfdc5","abstract_canon_sha256":"0cacba5c15e2711e3b3f44f6b884ce1aa2a96fdfe3d3e5e4400c4780da320874"},"schema_version":"1.0"},"canonical_sha256":"cdc63906b928eece0c39416f8aaf577ccd97bff45cfa8211b160a4890d3d5be4","source":{"kind":"arxiv","id":"2103.07084","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.07084","created_at":"2026-07-05T04:14:23Z"},{"alias_kind":"arxiv_version","alias_value":"2103.07084v2","created_at":"2026-07-05T04:14:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.07084","created_at":"2026-07-05T04:14:23Z"},{"alias_kind":"pith_short_12","alias_value":"ZXDDSBVZFDXM","created_at":"2026-07-05T04:14:23Z"},{"alias_kind":"pith_short_16","alias_value":"ZXDDSBVZFDXM4DBZ","created_at":"2026-07-05T04:14:23Z"},{"alias_kind":"pith_short_8","alias_value":"ZXDDSBVZ","created_at":"2026-07-05T04:14:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZXDDSBVZFDXM4DBZIFXYVL2XPT","target":"record","payload":{"canonical_record":{"source":{"id":"2103.07084","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2021-03-12T04:54:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"64fed99cc90007a0fa1d453ae76a03842b4a172ba9d0f408635f15d4d2ecfdc5","abstract_canon_sha256":"0cacba5c15e2711e3b3f44f6b884ce1aa2a96fdfe3d3e5e4400c4780da320874"},"schema_version":"1.0"},"canonical_sha256":"cdc63906b928eece0c39416f8aaf577ccd97bff45cfa8211b160a4890d3d5be4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:23.778329Z","signature_b64":"crTEZDU9HpynNz+cxWgpyH0C4m9i9KBeMry+aycvFLhRLEfWntcZhxOorGoMG7S82NWYBLZY+1TsNBYCNMd2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdc63906b928eece0c39416f8aaf577ccd97bff45cfa8211b160a4890d3d5be4","last_reissued_at":"2026-07-05T04:14:23.777911Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:23.777911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.07084","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:14:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xJDHlhEX9ygB2WbYPuVqv2tZsDs7Y7bcWpQ+FfTnTGMJ7ifJ89u4KkBlNmAOEv78kvyEWqzizlNRbdbf2YJaDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:38:40.089604Z"},"content_sha256":"ad8960699ed0d692aec564bb7c9c9c60fbd0e92063dd4204d195d5c75646bb79","schema_version":"1.0","event_id":"sha256:ad8960699ed0d692aec564bb7c9c9c60fbd0e92063dd4204d195d5c75646bb79"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZXDDSBVZFDXM4DBZIFXYVL2XPT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Information","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Masashi Sugiyama, Takayuki Osa, Voot Tangkaratt","submitted_at":"2021-03-12T04:54:31Z","abstract_excerpt":"Reinforcement learning algorithms are typically limited to learning a single solution for a specified task, even though diverse solutions often exist. Recent studies showed that learning a set of diverse solutions is beneficial because diversity enables robust few-shot adaptation. Although existing methods learn diverse solutions by using the mutual information as unsupervised rewards, such an approach often suffers from the bias of the gradient estimator induced by value function approximation. In this study, we propose a novel method that can learn diverse solutions without suffering the bia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.07084","kind":"arxiv","version":2},"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/2103.07084/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":"2026-07-05T04:14:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OVlgvwvzVMorKkVg4BFt0ZcZZZBKwE9xqBfr5dkH4idMm37g0DTTmv3cg0/Y9vdbiuDaHq44bf3cagSnsEDvCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:38:40.090006Z"},"content_sha256":"de7a9dde7631a705cd071b0bf18cb6ede1420af3e520d3e5150f6361abddd7bb","schema_version":"1.0","event_id":"sha256:de7a9dde7631a705cd071b0bf18cb6ede1420af3e520d3e5150f6361abddd7bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZXDDSBVZFDXM4DBZIFXYVL2XPT/bundle.json","state_url":"https://pith.science/pith/ZXDDSBVZFDXM4DBZIFXYVL2XPT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZXDDSBVZFDXM4DBZIFXYVL2XPT/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":"2026-07-06T19:38:40Z","links":{"resolver":"https://pith.science/pith/ZXDDSBVZFDXM4DBZIFXYVL2XPT","bundle":"https://pith.science/pith/ZXDDSBVZFDXM4DBZIFXYVL2XPT/bundle.json","state":"https://pith.science/pith/ZXDDSBVZFDXM4DBZIFXYVL2XPT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZXDDSBVZFDXM4DBZIFXYVL2XPT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZXDDSBVZFDXM4DBZIFXYVL2XPT","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":"0cacba5c15e2711e3b3f44f6b884ce1aa2a96fdfe3d3e5e4400c4780da320874","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2021-03-12T04:54:31Z","title_canon_sha256":"64fed99cc90007a0fa1d453ae76a03842b4a172ba9d0f408635f15d4d2ecfdc5"},"schema_version":"1.0","source":{"id":"2103.07084","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.07084","created_at":"2026-07-05T04:14:23Z"},{"alias_kind":"arxiv_version","alias_value":"2103.07084v2","created_at":"2026-07-05T04:14:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.07084","created_at":"2026-07-05T04:14:23Z"},{"alias_kind":"pith_short_12","alias_value":"ZXDDSBVZFDXM","created_at":"2026-07-05T04:14:23Z"},{"alias_kind":"pith_short_16","alias_value":"ZXDDSBVZFDXM4DBZ","created_at":"2026-07-05T04:14:23Z"},{"alias_kind":"pith_short_8","alias_value":"ZXDDSBVZ","created_at":"2026-07-05T04:14:23Z"}],"graph_snapshots":[{"event_id":"sha256:de7a9dde7631a705cd071b0bf18cb6ede1420af3e520d3e5150f6361abddd7bb","target":"graph","created_at":"2026-07-05T04:14:23Z","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/2103.07084/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning algorithms are typically limited to learning a single solution for a specified task, even though diverse solutions often exist. Recent studies showed that learning a set of diverse solutions is beneficial because diversity enables robust few-shot adaptation. Although existing methods learn diverse solutions by using the mutual information as unsupervised rewards, such an approach often suffers from the bias of the gradient estimator induced by value function approximation. In this study, we propose a novel method that can learn diverse solutions without suffering the bia","authors_text":"Masashi Sugiyama, Takayuki Osa, Voot Tangkaratt","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2021-03-12T04:54:31Z","title":"Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.07084","kind":"arxiv","version":2},"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:ad8960699ed0d692aec564bb7c9c9c60fbd0e92063dd4204d195d5c75646bb79","target":"record","created_at":"2026-07-05T04:14:23Z","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":"0cacba5c15e2711e3b3f44f6b884ce1aa2a96fdfe3d3e5e4400c4780da320874","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2021-03-12T04:54:31Z","title_canon_sha256":"64fed99cc90007a0fa1d453ae76a03842b4a172ba9d0f408635f15d4d2ecfdc5"},"schema_version":"1.0","source":{"id":"2103.07084","kind":"arxiv","version":2}},"canonical_sha256":"cdc63906b928eece0c39416f8aaf577ccd97bff45cfa8211b160a4890d3d5be4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cdc63906b928eece0c39416f8aaf577ccd97bff45cfa8211b160a4890d3d5be4","first_computed_at":"2026-07-05T04:14:23.777911Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:14:23.777911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"crTEZDU9HpynNz+cxWgpyH0C4m9i9KBeMry+aycvFLhRLEfWntcZhxOorGoMG7S82NWYBLZY+1TsNBYCNMd2Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:14:23.778329Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.07084","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad8960699ed0d692aec564bb7c9c9c60fbd0e92063dd4204d195d5c75646bb79","sha256:de7a9dde7631a705cd071b0bf18cb6ede1420af3e520d3e5150f6361abddd7bb"],"state_sha256":"04d02a0d106947baedb334f1f233fcbbea47e802b5ef92139b2c9227e795e737"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JhfW5UlNz7Q2cvak6RwVDmMWDCXw8UFu6Gkqkp3Z+AMCXjLYwvZqWwIBs4mNBPQtS+Mz26A6yVZqrlk6Nhj2CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:38:40.092014Z","bundle_sha256":"84d27cd30dfe8275d54f9ad9670044091cdac0086c1cc845257248029774dee2"}}