{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:MDBQ2OA4OMMOEEBPZKDEZFPV6Q","short_pith_number":"pith:MDBQ2OA4","canonical_record":{"source":{"id":"2205.07015","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-14T09:08:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"09ff0025a2344dd431272182289ac333f4a72d3abcbe5e5dc93fcd6b5c23d5c1","abstract_canon_sha256":"0ed17d0e88b51c273fc90cc43870cd9c60c3a2345dc96f6337fb992d5c8bbc05"},"schema_version":"1.0"},"canonical_sha256":"60c30d381c7318e2102fca864c95f5f4387eed911e06a0dcd38ae15337d1ac3d","source":{"kind":"arxiv","id":"2205.07015","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.07015","created_at":"2026-07-05T04:59:53Z"},{"alias_kind":"arxiv_version","alias_value":"2205.07015v3","created_at":"2026-07-05T04:59:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.07015","created_at":"2026-07-05T04:59:53Z"},{"alias_kind":"pith_short_12","alias_value":"MDBQ2OA4OMMO","created_at":"2026-07-05T04:59:53Z"},{"alias_kind":"pith_short_16","alias_value":"MDBQ2OA4OMMOEEBP","created_at":"2026-07-05T04:59:53Z"},{"alias_kind":"pith_short_8","alias_value":"MDBQ2OA4","created_at":"2026-07-05T04:59:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:MDBQ2OA4OMMOEEBPZKDEZFPV6Q","target":"record","payload":{"canonical_record":{"source":{"id":"2205.07015","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-14T09:08:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"09ff0025a2344dd431272182289ac333f4a72d3abcbe5e5dc93fcd6b5c23d5c1","abstract_canon_sha256":"0ed17d0e88b51c273fc90cc43870cd9c60c3a2345dc96f6337fb992d5c8bbc05"},"schema_version":"1.0"},"canonical_sha256":"60c30d381c7318e2102fca864c95f5f4387eed911e06a0dcd38ae15337d1ac3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:59:53.373240Z","signature_b64":"684K4SKn+ezM0fZDXZiI4nNsVMVLNmcifjGcCfVqykjQH6q5s6s5/c9b+B8yVdJJFXVED0E2/3AAmswOsK44Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60c30d381c7318e2102fca864c95f5f4387eed911e06a0dcd38ae15337d1ac3d","last_reissued_at":"2026-07-05T04:59:53.372825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:59:53.372825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.07015","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:59:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZICmg9tghILKz6GoqqA+ac/9fzV52g8QthqGB1MFcAyHmstEK3exxfejziVirPPCjd6kAXh5k+HHTONm+ESXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:45:24.526371Z"},"content_sha256":"bcb3d640ef18889413a0e97268dd189c8783df71dcb6314dfdf06e02e5d767a9","schema_version":"1.0","event_id":"sha256:bcb3d640ef18889413a0e97268dd189c8783df71dcb6314dfdf06e02e5d767a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:MDBQ2OA4OMMOEEBPZKDEZFPV6Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benjamin Black, J. K. Terry, John P. Dickerson, Ryan Sullivan","submitted_at":"2022-05-14T09:08:29Z","abstract_excerpt":"Visualizing optimization landscapes has led to many fundamental insights in numeric optimization, and novel improvements to optimization techniques. However, visualizations of the objective that reinforcement learning optimizes (the \"reward surface\") have only ever been generated for a small number of narrow contexts. This work presents reward surfaces and related visualizations of 27 of the most widely used reinforcement learning environments in Gym for the first time. We also explore reward surfaces in the policy gradient direction and show for the first time that many popular reinforcement "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.07015","kind":"arxiv","version":3},"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/2205.07015/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":"2026-07-05T04:59:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t/cZvT8n8xrZvURJ6oZnRb/RdPDLYXhce/i2OCE3L7gI4AVWXK1FEDsFxFZboLBzPVcoYChArp0rF96gcITMDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:45:24.526751Z"},"content_sha256":"df9abb17fd979fa21b2ccde1d4b91fd936f8effe67693197ce9eeb6862d3d95a","schema_version":"1.0","event_id":"sha256:df9abb17fd979fa21b2ccde1d4b91fd936f8effe67693197ce9eeb6862d3d95a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MDBQ2OA4OMMOEEBPZKDEZFPV6Q/bundle.json","state_url":"https://pith.science/pith/MDBQ2OA4OMMOEEBPZKDEZFPV6Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MDBQ2OA4OMMOEEBPZKDEZFPV6Q/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":"2026-07-07T13:45:24Z","links":{"resolver":"https://pith.science/pith/MDBQ2OA4OMMOEEBPZKDEZFPV6Q","bundle":"https://pith.science/pith/MDBQ2OA4OMMOEEBPZKDEZFPV6Q/bundle.json","state":"https://pith.science/pith/MDBQ2OA4OMMOEEBPZKDEZFPV6Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MDBQ2OA4OMMOEEBPZKDEZFPV6Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MDBQ2OA4OMMOEEBPZKDEZFPV6Q","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":"0ed17d0e88b51c273fc90cc43870cd9c60c3a2345dc96f6337fb992d5c8bbc05","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-14T09:08:29Z","title_canon_sha256":"09ff0025a2344dd431272182289ac333f4a72d3abcbe5e5dc93fcd6b5c23d5c1"},"schema_version":"1.0","source":{"id":"2205.07015","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.07015","created_at":"2026-07-05T04:59:53Z"},{"alias_kind":"arxiv_version","alias_value":"2205.07015v3","created_at":"2026-07-05T04:59:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.07015","created_at":"2026-07-05T04:59:53Z"},{"alias_kind":"pith_short_12","alias_value":"MDBQ2OA4OMMO","created_at":"2026-07-05T04:59:53Z"},{"alias_kind":"pith_short_16","alias_value":"MDBQ2OA4OMMOEEBP","created_at":"2026-07-05T04:59:53Z"},{"alias_kind":"pith_short_8","alias_value":"MDBQ2OA4","created_at":"2026-07-05T04:59:53Z"}],"graph_snapshots":[{"event_id":"sha256:df9abb17fd979fa21b2ccde1d4b91fd936f8effe67693197ce9eeb6862d3d95a","target":"graph","created_at":"2026-07-05T04:59:53Z","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/2205.07015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visualizing optimization landscapes has led to many fundamental insights in numeric optimization, and novel improvements to optimization techniques. However, visualizations of the objective that reinforcement learning optimizes (the \"reward surface\") have only ever been generated for a small number of narrow contexts. This work presents reward surfaces and related visualizations of 27 of the most widely used reinforcement learning environments in Gym for the first time. We also explore reward surfaces in the policy gradient direction and show for the first time that many popular reinforcement ","authors_text":"Benjamin Black, J. K. Terry, John P. Dickerson, Ryan Sullivan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-14T09:08:29Z","title":"Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.07015","kind":"arxiv","version":3},"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:bcb3d640ef18889413a0e97268dd189c8783df71dcb6314dfdf06e02e5d767a9","target":"record","created_at":"2026-07-05T04:59:53Z","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":"0ed17d0e88b51c273fc90cc43870cd9c60c3a2345dc96f6337fb992d5c8bbc05","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-14T09:08:29Z","title_canon_sha256":"09ff0025a2344dd431272182289ac333f4a72d3abcbe5e5dc93fcd6b5c23d5c1"},"schema_version":"1.0","source":{"id":"2205.07015","kind":"arxiv","version":3}},"canonical_sha256":"60c30d381c7318e2102fca864c95f5f4387eed911e06a0dcd38ae15337d1ac3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60c30d381c7318e2102fca864c95f5f4387eed911e06a0dcd38ae15337d1ac3d","first_computed_at":"2026-07-05T04:59:53.372825Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:59:53.372825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"684K4SKn+ezM0fZDXZiI4nNsVMVLNmcifjGcCfVqykjQH6q5s6s5/c9b+B8yVdJJFXVED0E2/3AAmswOsK44Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:59:53.373240Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.07015","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcb3d640ef18889413a0e97268dd189c8783df71dcb6314dfdf06e02e5d767a9","sha256:df9abb17fd979fa21b2ccde1d4b91fd936f8effe67693197ce9eeb6862d3d95a"],"state_sha256":"3f12568014c938b551ae092f88df2911708f14dedc9b2ec593d034830350c450"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k2FQwYFFt6GEnzNTa9TeUW/ANnv7duJluQ25vag3ZeysMinQLnwwQuucK3OX0JOqpsMTL/D8Utsq1N2/zZ8JBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:45:24.529260Z","bundle_sha256":"1e610ef81df17b45cba9e49f20149acfe63c930c75813d11af0549fef78288ed"}}