{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6UO4YP6CF7XI2YUR7BW54ZJZNJ","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":"1d5d660ac421b3aea40f2e48561de70144905543b14b5368dba871e5deb8ab65","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-21T06:38:46Z","title_canon_sha256":"9f50471a2df0c90a9d16b2409f24be6e1d5a069736f23bf400e40702287c4e60"},"schema_version":"1.0","source":{"id":"2507.15287","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15287","created_at":"2026-07-05T11:40:22Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15287v1","created_at":"2026-07-05T11:40:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15287","created_at":"2026-07-05T11:40:22Z"},{"alias_kind":"pith_short_12","alias_value":"6UO4YP6CF7XI","created_at":"2026-07-05T11:40:22Z"},{"alias_kind":"pith_short_16","alias_value":"6UO4YP6CF7XI2YUR","created_at":"2026-07-05T11:40:22Z"},{"alias_kind":"pith_short_8","alias_value":"6UO4YP6C","created_at":"2026-07-05T11:40:22Z"}],"graph_snapshots":[{"event_id":"sha256:5a2940da4a839621e4f04480dfdf02ad3f3dbd49c7d506a074de390ab025f576","target":"graph","created_at":"2026-07-05T11:40:22Z","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/2507.15287/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent trends in Reinforcement Learning (RL) highlight the need for agents to learn from reward-free interactions and alternative supervision signals, such as unlabeled or incomplete demonstrations, rather than relying solely on explicit reward maximization. Additionally, developing generalist agents that can adapt efficiently in real-world environments often requires leveraging these reward-free signals to guide learning and behavior. However, while intrinsic motivation techniques provide a means for agents to seek out novel or uncertain states in the absence of explicit rewards, they are oft","authors_text":"Elias Malomgr\\'e, Pieter Simoens","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-21T06:38:46Z","title":"Mixture of Autoencoder Experts Guidance using Unlabeled and Incomplete Data for Exploration in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15287","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":"sha256:046b28a3a3a12fcc9230437d115c9270e37576ecfda84dedcf4f881ad59a83eb","target":"record","created_at":"2026-07-05T11:40:22Z","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":"1d5d660ac421b3aea40f2e48561de70144905543b14b5368dba871e5deb8ab65","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-21T06:38:46Z","title_canon_sha256":"9f50471a2df0c90a9d16b2409f24be6e1d5a069736f23bf400e40702287c4e60"},"schema_version":"1.0","source":{"id":"2507.15287","kind":"arxiv","version":1}},"canonical_sha256":"f51dcc3fc22fee8d6291f86dde65396a7c1d6cf0f79a573d3e10078cae3fd16e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f51dcc3fc22fee8d6291f86dde65396a7c1d6cf0f79a573d3e10078cae3fd16e","first_computed_at":"2026-07-05T11:40:22.040867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:22.040867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VxsRbYglXmFkiXuwAxmeukDzPjShe/IO9WFIWgeDZprJxsAK6jJvFaGgQw0TDtQuURpJGxANx033oR82ggr0DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:22.041359Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15287","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:046b28a3a3a12fcc9230437d115c9270e37576ecfda84dedcf4f881ad59a83eb","sha256:5a2940da4a839621e4f04480dfdf02ad3f3dbd49c7d506a074de390ab025f576"],"state_sha256":"94a62e90aa5f0ed31d68af0964927eb608daa39c696c2a03e4f40ed322d8029d"}