{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2IEMHEDGGTXWNF6KBJ274IOAO4","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":"3305f20fc27b6b7449d0d60eccb1c8acdd99c211742b574b1f84cd64835b0b55","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T15:20:32Z","title_canon_sha256":"7f3576dfb9e59c59eb5fc7cef17bb50095bdccc5731c4d9db55dff6243be416b"},"schema_version":"1.0","source":{"id":"2502.04141","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04141","created_at":"2026-07-05T10:10:34Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04141v1","created_at":"2026-07-05T10:10:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04141","created_at":"2026-07-05T10:10:34Z"},{"alias_kind":"pith_short_12","alias_value":"2IEMHEDGGTXW","created_at":"2026-07-05T10:10:34Z"},{"alias_kind":"pith_short_16","alias_value":"2IEMHEDGGTXWNF6K","created_at":"2026-07-05T10:10:34Z"},{"alias_kind":"pith_short_8","alias_value":"2IEMHEDG","created_at":"2026-07-05T10:10:34Z"}],"graph_snapshots":[{"event_id":"sha256:8c1b27954b03a33bff0652657ed854d4eba78bd38513faa0949846f743b4133f","target":"graph","created_at":"2026-07-05T10:10:34Z","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/2502.04141/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Entropy-based objectives are widely used to perform state space exploration in reinforcement learning (RL) and dataset generation for offline RL. Behavioral entropy (BE), a rigorous generalization of classical entropies that incorporates cognitive and perceptual biases of agents, was recently proposed for discrete settings and shown to be a promising metric for robotic exploration problems. In this work, we propose using BE as a principled exploration objective for systematically generating datasets that provide diverse state space coverage in complex, continuous, potentially high-dimensional ","authors_text":"Aamodh Suresh, Carlos Nieto-Granda, Wesley A. Suttle","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T15:20:32Z","title":"Behavioral Entropy-Guided Dataset Generation for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04141","kind":"arxiv","version":1},"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":"sha256:20eff7cfd9e9aac5e8cdd97181032005ae3ee67e3f011635dc758eb6a4528e9a","target":"record","created_at":"2026-07-05T10:10:34Z","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":"3305f20fc27b6b7449d0d60eccb1c8acdd99c211742b574b1f84cd64835b0b55","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T15:20:32Z","title_canon_sha256":"7f3576dfb9e59c59eb5fc7cef17bb50095bdccc5731c4d9db55dff6243be416b"},"schema_version":"1.0","source":{"id":"2502.04141","kind":"arxiv","version":1}},"canonical_sha256":"d208c3906634ef6697ca0a75fe21c07736789fa218ad505f013d06ef18e6014f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d208c3906634ef6697ca0a75fe21c07736789fa218ad505f013d06ef18e6014f","first_computed_at":"2026-07-05T10:10:34.535256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:34.535256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kLFsjf5yfFnFf2BOmRloii+9U8ja1JmRYkCRDy+j5/Am9yTnS5QZ7kblPjDD9Vf5gzQt/RGkIWigWALTtcwOBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:34.535701Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04141","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20eff7cfd9e9aac5e8cdd97181032005ae3ee67e3f011635dc758eb6a4528e9a","sha256:8c1b27954b03a33bff0652657ed854d4eba78bd38513faa0949846f743b4133f"],"state_sha256":"230847f00b4365caf372b70da9ddfe544b8c4a5674ef41391f8c70ea7f6c21ff"}