{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6UO4YP6CF7XI2YUR7BW54ZJZNJ","short_pith_number":"pith:6UO4YP6C","schema_version":"1.0","canonical_sha256":"f51dcc3fc22fee8d6291f86dde65396a7c1d6cf0f79a573d3e10078cae3fd16e","source":{"kind":"arxiv","id":"2507.15287","version":1},"attestation_state":"computed","paper":{"title":"Mixture of Autoencoder Experts Guidance using Unlabeled and Incomplete Data for Exploration in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Elias Malomgr\\'e, Pieter Simoens","submitted_at":"2025-07-21T06:38:46Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.15287","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-21T06:38:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9f50471a2df0c90a9d16b2409f24be6e1d5a069736f23bf400e40702287c4e60","abstract_canon_sha256":"1d5d660ac421b3aea40f2e48561de70144905543b14b5368dba871e5deb8ab65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:22.041359Z","signature_b64":"VxsRbYglXmFkiXuwAxmeukDzPjShe/IO9WFIWgeDZprJxsAK6jJvFaGgQw0TDtQuURpJGxANx033oR82ggr0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f51dcc3fc22fee8d6291f86dde65396a7c1d6cf0f79a573d3e10078cae3fd16e","last_reissued_at":"2026-07-05T11:40:22.040867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:22.040867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mixture of Autoencoder Experts Guidance using Unlabeled and Incomplete Data for Exploration in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Elias Malomgr\\'e, Pieter Simoens","submitted_at":"2025-07-21T06:38:46Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15287","kind":"arxiv","version":1},"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/2507.15287/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.15287","created_at":"2026-07-05T11:40:22.040926+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.15287v1","created_at":"2026-07-05T11:40:22.040926+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15287","created_at":"2026-07-05T11:40:22.040926+00:00"},{"alias_kind":"pith_short_12","alias_value":"6UO4YP6CF7XI","created_at":"2026-07-05T11:40:22.040926+00:00"},{"alias_kind":"pith_short_16","alias_value":"6UO4YP6CF7XI2YUR","created_at":"2026-07-05T11:40:22.040926+00:00"},{"alias_kind":"pith_short_8","alias_value":"6UO4YP6C","created_at":"2026-07-05T11:40:22.040926+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.02259","citing_title":"The Alignment Flywheel: A Governance-Centric Hybrid MAS for Architecture-Agnostic Safety","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6UO4YP6CF7XI2YUR7BW54ZJZNJ","json":"https://pith.science/pith/6UO4YP6CF7XI2YUR7BW54ZJZNJ.json","graph_json":"https://pith.science/api/pith-number/6UO4YP6CF7XI2YUR7BW54ZJZNJ/graph.json","events_json":"https://pith.science/api/pith-number/6UO4YP6CF7XI2YUR7BW54ZJZNJ/events.json","paper":"https://pith.science/paper/6UO4YP6C"},"agent_actions":{"view_html":"https://pith.science/pith/6UO4YP6CF7XI2YUR7BW54ZJZNJ","download_json":"https://pith.science/pith/6UO4YP6CF7XI2YUR7BW54ZJZNJ.json","view_paper":"https://pith.science/paper/6UO4YP6C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.15287&json=true","fetch_graph":"https://pith.science/api/pith-number/6UO4YP6CF7XI2YUR7BW54ZJZNJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6UO4YP6CF7XI2YUR7BW54ZJZNJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6UO4YP6CF7XI2YUR7BW54ZJZNJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6UO4YP6CF7XI2YUR7BW54ZJZNJ/action/storage_attestation","attest_author":"https://pith.science/pith/6UO4YP6CF7XI2YUR7BW54ZJZNJ/action/author_attestation","sign_citation":"https://pith.science/pith/6UO4YP6CF7XI2YUR7BW54ZJZNJ/action/citation_signature","submit_replication":"https://pith.science/pith/6UO4YP6CF7XI2YUR7BW54ZJZNJ/action/replication_record"}},"created_at":"2026-07-05T11:40:22.040926+00:00","updated_at":"2026-07-05T11:40:22.040926+00:00"}