{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Z3FQQSFTMUOOGPM3OMVXVNCKKD","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":"d6ec39fd717d66c6fb389588172087f402d47e437df7444d70aba5dc2a2b3bb7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-02-22T18:58:09Z","title_canon_sha256":"b8d0fbb63674d40c3e75e35219e30a37ad9aeef3029e797a443046f66c573d36"},"schema_version":"1.0","source":{"id":"2302.11563","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.11563","created_at":"2026-07-05T08:29:44Z"},{"alias_kind":"arxiv_version","alias_value":"2302.11563v4","created_at":"2026-07-05T08:29:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11563","created_at":"2026-07-05T08:29:44Z"},{"alias_kind":"pith_short_12","alias_value":"Z3FQQSFTMUOO","created_at":"2026-07-05T08:29:44Z"},{"alias_kind":"pith_short_16","alias_value":"Z3FQQSFTMUOOGPM3","created_at":"2026-07-05T08:29:44Z"},{"alias_kind":"pith_short_8","alias_value":"Z3FQQSFT","created_at":"2026-07-05T08:29:44Z"}],"graph_snapshots":[{"event_id":"sha256:04f75fc308fe7b36b736138ea77668736886f0d9ec484695b09f7dae5793d288","target":"graph","created_at":"2026-07-05T08:29:44Z","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/2302.11563/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning can solve decision-making problems and train an agent to behave in an environment according to a predesigned reward function. However, such an approach becomes very problematic if the reward is too sparse and so the agent does not come across the reward during the environmental exploration. The solution to such a problem may be to equip the agent with an intrinsic motivation that will provide informed exploration during which the agent is likely to also encounter external reward. Novelty detection is one of the promising branches of intrinsic motivation research. We pres","authors_text":"Igor Farka\\v{s}, Matej Pech\\'a\\v{c}, Michal Chovanec","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-02-22T18:58:09Z","title":"Self-supervised network distillation: an effective approach to exploration in sparse reward environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11563","kind":"arxiv","version":4},"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:ccae63a3818aea98f13cd068b013099dd1079e08361384708b33070a26a9b6fe","target":"record","created_at":"2026-07-05T08:29:44Z","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":"d6ec39fd717d66c6fb389588172087f402d47e437df7444d70aba5dc2a2b3bb7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-02-22T18:58:09Z","title_canon_sha256":"b8d0fbb63674d40c3e75e35219e30a37ad9aeef3029e797a443046f66c573d36"},"schema_version":"1.0","source":{"id":"2302.11563","kind":"arxiv","version":4}},"canonical_sha256":"cecb0848b3651ce33d9b732b7ab44a50ecfe4cb5a8165dd2d1202e63be433822","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cecb0848b3651ce33d9b732b7ab44a50ecfe4cb5a8165dd2d1202e63be433822","first_computed_at":"2026-07-05T08:29:44.037859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:44.037859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TT3CVikQvDJUPMcNBlY5yMqxDIEFCjwbEzIPS8Fqe+lq5xgH9yCd7XNX9/nCJ9cMU3J+AItXn6iw+5n2i+9XDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:44.038270Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.11563","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccae63a3818aea98f13cd068b013099dd1079e08361384708b33070a26a9b6fe","sha256:04f75fc308fe7b36b736138ea77668736886f0d9ec484695b09f7dae5793d288"],"state_sha256":"3fd09a6df054c8cb4ddf42b717cad9f04036b6b393e4933c2d4f7c272e8a80bc"}