{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:OV4HMMVPSMIQ5ABHDBSQE353AN","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":"a62dfc435bcc53696440e725dad692a81a04ddd945288e5e300eb051527412bf","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-11T18:19:11Z","title_canon_sha256":"46acb27fca211e47618460ee0a475d34df47d7c56f1d7c44f3853b41f37280ec"},"schema_version":"1.0","source":{"id":"1912.05510","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.05510","created_at":"2026-07-05T02:13:12Z"},{"alias_kind":"arxiv_version","alias_value":"1912.05510v4","created_at":"2026-07-05T02:13:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.05510","created_at":"2026-07-05T02:13:12Z"},{"alias_kind":"pith_short_12","alias_value":"OV4HMMVPSMIQ","created_at":"2026-07-05T02:13:12Z"},{"alias_kind":"pith_short_16","alias_value":"OV4HMMVPSMIQ5ABH","created_at":"2026-07-05T02:13:12Z"},{"alias_kind":"pith_short_8","alias_value":"OV4HMMVP","created_at":"2026-07-05T02:13:12Z"}],"graph_snapshots":[{"event_id":"sha256:3dbb02581c52786676399b7143cc9a739219a5c64417e9a047d922ecaac8e177","target":"graph","created_at":"2026-07-05T02:13:12Z","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/1912.05510/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Every living organism struggles against disruptive environmental forces to carve out and maintain an orderly niche. We propose that such a struggle to achieve and preserve order might offer a principle for the emergence of useful behaviors in artificial agents. We formalize this idea into an unsupervised reinforcement learning method called surprise minimizing reinforcement learning (SMiRL). SMiRL alternates between learning a density model to evaluate the surprise of a stimulus, and improving the policy to seek more predictable stimuli. The policy seeks out stable and repeatable situations th","authors_text":"Chelsea Finn, Coline Devin, Daniel Geng, Dinesh Jayaraman, Glen Berseth, Nicholas Rhinehart, Sergey Levine","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-11T18:19:11Z","title":"SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.05510","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:b911dc52e8560fdb7f28fb7b8c4e21710965c468ab9b4a1901c5fab60f06a6ec","target":"record","created_at":"2026-07-05T02:13:12Z","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":"a62dfc435bcc53696440e725dad692a81a04ddd945288e5e300eb051527412bf","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-11T18:19:11Z","title_canon_sha256":"46acb27fca211e47618460ee0a475d34df47d7c56f1d7c44f3853b41f37280ec"},"schema_version":"1.0","source":{"id":"1912.05510","kind":"arxiv","version":4}},"canonical_sha256":"75787632af93110e80271865026fbb037e22bc746fe6317228a4b58be8855ac6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75787632af93110e80271865026fbb037e22bc746fe6317228a4b58be8855ac6","first_computed_at":"2026-07-05T02:13:12.134778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:13:12.134778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UoEJHiwlMcmrQKL2w6Vi9l3ut+XzDem1QE7doucGnuQhii+53udFmp1Qnr1uZMvAtn/kf/XPVUOWG+hNsoRTBw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:13:12.135220Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.05510","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b911dc52e8560fdb7f28fb7b8c4e21710965c468ab9b4a1901c5fab60f06a6ec","sha256:3dbb02581c52786676399b7143cc9a739219a5c64417e9a047d922ecaac8e177"],"state_sha256":"743a289f37e49f45ecef60d47541005b8b206d5316cf2a47ba7f76ec3695b9df"}