{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:26ZDT4YACXOLVDVLTUC7BJVQTW","short_pith_number":"pith:26ZDT4YA","canonical_record":{"source":{"id":"2205.10484","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-21T01:52:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d74116dec4dd493bbffa1497778daa452b9a18dbfc30a068d5a88759ff6ce30e","abstract_canon_sha256":"439b0aaba89bd7cb9b30f06870984518b00068f63fd6c2613dbb994ec9b9b740"},"schema_version":"1.0"},"canonical_sha256":"d7b239f30015dcba8eab9d05f0a6b09db001a75566b4b306b1ee4cbcc31c27fe","source":{"kind":"arxiv","id":"2205.10484","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.10484","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"arxiv_version","alias_value":"2205.10484v2","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10484","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"pith_short_12","alias_value":"26ZDT4YACXOL","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"pith_short_16","alias_value":"26ZDT4YACXOLVDVL","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"pith_short_8","alias_value":"26ZDT4YA","created_at":"2026-07-05T04:27:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:26ZDT4YACXOLVDVLTUC7BJVQTW","target":"record","payload":{"canonical_record":{"source":{"id":"2205.10484","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-21T01:52:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d74116dec4dd493bbffa1497778daa452b9a18dbfc30a068d5a88759ff6ce30e","abstract_canon_sha256":"439b0aaba89bd7cb9b30f06870984518b00068f63fd6c2613dbb994ec9b9b740"},"schema_version":"1.0"},"canonical_sha256":"d7b239f30015dcba8eab9d05f0a6b09db001a75566b4b306b1ee4cbcc31c27fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:13.937223Z","signature_b64":"DwNYHzE39MwiB+vyIG/x+oWmGnt1C9xBdl5bppRIquTWq49NwCkipYjFGhKQ1kSbYVa2aUcc7gJnfp6A9z48Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7b239f30015dcba8eab9d05f0a6b09db001a75566b4b306b1ee4cbcc31c27fe","last_reissued_at":"2026-07-05T04:27:13.936850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:13.936850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.10484","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":"2026-07-05T04:27:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1KyFLspAnyp1OBpLy8WlX0m14eBV8PY6KTkY9dMQDr3hydxqOgP3n3PZwCnyd74iBU7NbblRJDXEtJ/PFI5dAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:40:24.592510Z"},"content_sha256":"1e42a75e2cf0178824ea0fd98c3a546579a8fc3cbd0c9b511ca2336b67d5ba57","schema_version":"1.0","event_id":"sha256:1e42a75e2cf0178824ea0fd98c3a546579a8fc3cbd0c9b511ca2336b67d5ba57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:26ZDT4YACXOLVDVLTUC7BJVQTW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nuclear Norm Maximization Based Curiosity-Driven Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Ding, Chao Chen, Dawei Feng, Huaimin Wang, Kele Xu, Sen Yang, Yiying Li, Zijian Gao","submitted_at":"2022-05-21T01:52:47Z","abstract_excerpt":"To handle the sparsity of the extrinsic rewards in reinforcement learning, researchers have proposed intrinsic reward which enables the agent to learn the skills that might come in handy for pursuing the rewards in the future, such as encouraging the agent to visit novel states. However, the intrinsic reward can be noisy due to the undesirable environment's stochasticity and directly applying the noisy value predictions to supervise the policy is detrimental to improve the learning performance and efficiency. Moreover, many previous studies employ $\\ell^2$ norm or variance to measure the explo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10484","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/2205.10484/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":"2026-07-05T04:27:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3RdNwJGHqfdW4QTFprFKlhX0HCnOHLo/VP5RzqrIqYHQsfy4rPUKN9QCUZriJjPanm4Pp1HjV3weIx6AzkajCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:40:24.593004Z"},"content_sha256":"7a11086d2fe5dc4a3c96ffa7646bb4c4fb32ec7b50c1545fcda04493f409a7be","schema_version":"1.0","event_id":"sha256:7a11086d2fe5dc4a3c96ffa7646bb4c4fb32ec7b50c1545fcda04493f409a7be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/26ZDT4YACXOLVDVLTUC7BJVQTW/bundle.json","state_url":"https://pith.science/pith/26ZDT4YACXOLVDVLTUC7BJVQTW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/26ZDT4YACXOLVDVLTUC7BJVQTW/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":"2026-08-05T15:40:24Z","links":{"resolver":"https://pith.science/pith/26ZDT4YACXOLVDVLTUC7BJVQTW","bundle":"https://pith.science/pith/26ZDT4YACXOLVDVLTUC7BJVQTW/bundle.json","state":"https://pith.science/pith/26ZDT4YACXOLVDVLTUC7BJVQTW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/26ZDT4YACXOLVDVLTUC7BJVQTW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:26ZDT4YACXOLVDVLTUC7BJVQTW","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":"439b0aaba89bd7cb9b30f06870984518b00068f63fd6c2613dbb994ec9b9b740","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-21T01:52:47Z","title_canon_sha256":"d74116dec4dd493bbffa1497778daa452b9a18dbfc30a068d5a88759ff6ce30e"},"schema_version":"1.0","source":{"id":"2205.10484","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.10484","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"arxiv_version","alias_value":"2205.10484v2","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10484","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"pith_short_12","alias_value":"26ZDT4YACXOL","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"pith_short_16","alias_value":"26ZDT4YACXOLVDVL","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"pith_short_8","alias_value":"26ZDT4YA","created_at":"2026-07-05T04:27:13Z"}],"graph_snapshots":[{"event_id":"sha256:7a11086d2fe5dc4a3c96ffa7646bb4c4fb32ec7b50c1545fcda04493f409a7be","target":"graph","created_at":"2026-07-05T04:27:13Z","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/2205.10484/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To handle the sparsity of the extrinsic rewards in reinforcement learning, researchers have proposed intrinsic reward which enables the agent to learn the skills that might come in handy for pursuing the rewards in the future, such as encouraging the agent to visit novel states. However, the intrinsic reward can be noisy due to the undesirable environment's stochasticity and directly applying the noisy value predictions to supervise the policy is detrimental to improve the learning performance and efficiency. Moreover, many previous studies employ $\\ell^2$ norm or variance to measure the explo","authors_text":"Bo Ding, Chao Chen, Dawei Feng, Huaimin Wang, Kele Xu, Sen Yang, Yiying Li, Zijian Gao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-21T01:52:47Z","title":"Nuclear Norm Maximization Based Curiosity-Driven Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10484","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":"sha256:1e42a75e2cf0178824ea0fd98c3a546579a8fc3cbd0c9b511ca2336b67d5ba57","target":"record","created_at":"2026-07-05T04:27:13Z","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":"439b0aaba89bd7cb9b30f06870984518b00068f63fd6c2613dbb994ec9b9b740","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-21T01:52:47Z","title_canon_sha256":"d74116dec4dd493bbffa1497778daa452b9a18dbfc30a068d5a88759ff6ce30e"},"schema_version":"1.0","source":{"id":"2205.10484","kind":"arxiv","version":2}},"canonical_sha256":"d7b239f30015dcba8eab9d05f0a6b09db001a75566b4b306b1ee4cbcc31c27fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7b239f30015dcba8eab9d05f0a6b09db001a75566b4b306b1ee4cbcc31c27fe","first_computed_at":"2026-07-05T04:27:13.936850Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:13.936850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DwNYHzE39MwiB+vyIG/x+oWmGnt1C9xBdl5bppRIquTWq49NwCkipYjFGhKQ1kSbYVa2aUcc7gJnfp6A9z48Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:13.937223Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.10484","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e42a75e2cf0178824ea0fd98c3a546579a8fc3cbd0c9b511ca2336b67d5ba57","sha256:7a11086d2fe5dc4a3c96ffa7646bb4c4fb32ec7b50c1545fcda04493f409a7be"],"state_sha256":"9637bc659fa9bdd8f5898a780757607e5f17d03b5bffac8e137b4b3165bca16e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"snJtwGDTxHQkoX+Smuwo/npgy34opdt7kW0FHLut7lVSf1T8wgyVx9dD2suj5cHL6qm/V0JWN/QZLo/XH1J9Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:40:24.597139Z","bundle_sha256":"83e610d176bc77274cb2fbc7439205e7bab9ed8ebf90f3ea50a8d113f96b932c"}}