{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:X36O2MCVW6YGY6N52EIFD3CYHN","short_pith_number":"pith:X36O2MCV","canonical_record":{"source":{"id":"2102.03765","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-07T10:28:09Z","cross_cats_sorted":[],"title_canon_sha256":"06217d8dbdd3006b15ffcba946605d89a1d8db8f46241233a02def8809f73ca0","abstract_canon_sha256":"428bdb29d23ce10ea3966dac2cfa72c7f6452e812b7e35bcfc61b0d15f36b91a"},"schema_version":"1.0"},"canonical_sha256":"befced3055b7b06c79bdd11051ec583b6b825d36c0b7f2b1fa34cac73acdc936","source":{"kind":"arxiv","id":"2102.03765","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.03765","created_at":"2026-07-05T04:12:00Z"},{"alias_kind":"arxiv_version","alias_value":"2102.03765v5","created_at":"2026-07-05T04:12:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.03765","created_at":"2026-07-05T04:12:00Z"},{"alias_kind":"pith_short_12","alias_value":"X36O2MCVW6YG","created_at":"2026-07-05T04:12:00Z"},{"alias_kind":"pith_short_16","alias_value":"X36O2MCVW6YGY6N5","created_at":"2026-07-05T04:12:00Z"},{"alias_kind":"pith_short_8","alias_value":"X36O2MCV","created_at":"2026-07-05T04:12:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:X36O2MCVW6YGY6N52EIFD3CYHN","target":"record","payload":{"canonical_record":{"source":{"id":"2102.03765","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-07T10:28:09Z","cross_cats_sorted":[],"title_canon_sha256":"06217d8dbdd3006b15ffcba946605d89a1d8db8f46241233a02def8809f73ca0","abstract_canon_sha256":"428bdb29d23ce10ea3966dac2cfa72c7f6452e812b7e35bcfc61b0d15f36b91a"},"schema_version":"1.0"},"canonical_sha256":"befced3055b7b06c79bdd11051ec583b6b825d36c0b7f2b1fa34cac73acdc936","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:00.875095Z","signature_b64":"inHh78lZKq8Y3yPv94r6UstigBTZJGFytR+FNA4q4UNq/NsxtbtpsPSY93kpiek3mRNjOTv9aN3OMU2eqYa7Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"befced3055b7b06c79bdd11051ec583b6b825d36c0b7f2b1fa34cac73acdc936","last_reissued_at":"2026-07-05T04:12:00.874554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:00.874554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.03765","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:12:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4EiWI3qY0HkvtVGlx7vJjIBqc4wSe5JqsmsxsEvXnb35G4TBRMp6JJf2fKdNLRGN5Ct21IvQKCDRLRuJC0B4Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:25:34.363015Z"},"content_sha256":"6b780647969b9fe6cd9397cef5703b1bb34a72a396c552d1e96604b75b829bf2","schema_version":"1.0","event_id":"sha256:6b780647969b9fe6cd9397cef5703b1bb34a72a396c552d1e96604b75b829bf2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:X36O2MCVW6YGY6N52EIFD3CYHN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tactical Optimism and Pessimism for Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aldo Pacchiano, Jack Parker-Holder, Michael Arbel, Michael I. Jordan, Ted Moskovitz","submitted_at":"2021-02-07T10:28:09Z","abstract_excerpt":"In recent years, deep off-policy actor-critic algorithms have become a dominant approach to reinforcement learning for continuous control. One of the primary drivers of this improved performance is the use of pessimistic value updates to address function approximation errors, which previously led to disappointing performance. However, a direct consequence of pessimism is reduced exploration, running counter to theoretical support for the efficacy of optimism in the face of uncertainty. So which approach is best? In this work, we show that the most effective degree of optimism can vary both acr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.03765","kind":"arxiv","version":5},"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/2102.03765/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":"2026-07-05T04:12:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"INAdPK4wObasfz+5sL7c8ZK6H39GQ27Yq0Qsl9n7RCrrQ14MjN1XoHocUI/PIc/xvPDYYVi+IfcI6crGUU4NBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:25:34.363508Z"},"content_sha256":"9363f36fd2be0805e85dee5058d7d970ea91a228f5d49c63f513cef8528bf657","schema_version":"1.0","event_id":"sha256:9363f36fd2be0805e85dee5058d7d970ea91a228f5d49c63f513cef8528bf657"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X36O2MCVW6YGY6N52EIFD3CYHN/bundle.json","state_url":"https://pith.science/pith/X36O2MCVW6YGY6N52EIFD3CYHN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X36O2MCVW6YGY6N52EIFD3CYHN/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":"2026-08-08T01:25:34Z","links":{"resolver":"https://pith.science/pith/X36O2MCVW6YGY6N52EIFD3CYHN","bundle":"https://pith.science/pith/X36O2MCVW6YGY6N52EIFD3CYHN/bundle.json","state":"https://pith.science/pith/X36O2MCVW6YGY6N52EIFD3CYHN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X36O2MCVW6YGY6N52EIFD3CYHN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:X36O2MCVW6YGY6N52EIFD3CYHN","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":"428bdb29d23ce10ea3966dac2cfa72c7f6452e812b7e35bcfc61b0d15f36b91a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-07T10:28:09Z","title_canon_sha256":"06217d8dbdd3006b15ffcba946605d89a1d8db8f46241233a02def8809f73ca0"},"schema_version":"1.0","source":{"id":"2102.03765","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.03765","created_at":"2026-07-05T04:12:00Z"},{"alias_kind":"arxiv_version","alias_value":"2102.03765v5","created_at":"2026-07-05T04:12:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.03765","created_at":"2026-07-05T04:12:00Z"},{"alias_kind":"pith_short_12","alias_value":"X36O2MCVW6YG","created_at":"2026-07-05T04:12:00Z"},{"alias_kind":"pith_short_16","alias_value":"X36O2MCVW6YGY6N5","created_at":"2026-07-05T04:12:00Z"},{"alias_kind":"pith_short_8","alias_value":"X36O2MCV","created_at":"2026-07-05T04:12:00Z"}],"graph_snapshots":[{"event_id":"sha256:9363f36fd2be0805e85dee5058d7d970ea91a228f5d49c63f513cef8528bf657","target":"graph","created_at":"2026-07-05T04:12:00Z","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/2102.03765/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, deep off-policy actor-critic algorithms have become a dominant approach to reinforcement learning for continuous control. One of the primary drivers of this improved performance is the use of pessimistic value updates to address function approximation errors, which previously led to disappointing performance. However, a direct consequence of pessimism is reduced exploration, running counter to theoretical support for the efficacy of optimism in the face of uncertainty. So which approach is best? In this work, we show that the most effective degree of optimism can vary both acr","authors_text":"Aldo Pacchiano, Jack Parker-Holder, Michael Arbel, Michael I. Jordan, Ted Moskovitz","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-07T10:28:09Z","title":"Tactical Optimism and Pessimism for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.03765","kind":"arxiv","version":5},"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":"sha256:6b780647969b9fe6cd9397cef5703b1bb34a72a396c552d1e96604b75b829bf2","target":"record","created_at":"2026-07-05T04:12:00Z","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":"428bdb29d23ce10ea3966dac2cfa72c7f6452e812b7e35bcfc61b0d15f36b91a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-07T10:28:09Z","title_canon_sha256":"06217d8dbdd3006b15ffcba946605d89a1d8db8f46241233a02def8809f73ca0"},"schema_version":"1.0","source":{"id":"2102.03765","kind":"arxiv","version":5}},"canonical_sha256":"befced3055b7b06c79bdd11051ec583b6b825d36c0b7f2b1fa34cac73acdc936","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"befced3055b7b06c79bdd11051ec583b6b825d36c0b7f2b1fa34cac73acdc936","first_computed_at":"2026-07-05T04:12:00.874554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:12:00.874554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"inHh78lZKq8Y3yPv94r6UstigBTZJGFytR+FNA4q4UNq/NsxtbtpsPSY93kpiek3mRNjOTv9aN3OMU2eqYa7Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:12:00.875095Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.03765","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b780647969b9fe6cd9397cef5703b1bb34a72a396c552d1e96604b75b829bf2","sha256:9363f36fd2be0805e85dee5058d7d970ea91a228f5d49c63f513cef8528bf657"],"state_sha256":"fb1778c51cd8b68b768d37f4ad2e3a28eb21ff643942bb1f4d5934611991c8f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mMkTu9SQDNU0MxyYE4keO0wWH6usCwLXbsKGeJkHbTYifD7SMFJdZR590GZEeKTeaAwaSUyXC6jsGaqT9s98Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:25:34.368398Z","bundle_sha256":"6784d08ab16f16ceed0c84d383989897be0bb01abad0ec02e6ba8d4b448d009c"}}