{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VGMSKL2GDHOUTFZEXIGG4V2EWV","short_pith_number":"pith:VGMSKL2G","schema_version":"1.0","canonical_sha256":"a999252f4619dd499724ba0c6e5744b5409ab9a07af0919ee1574becc7f213a9","source":{"kind":"arxiv","id":"2506.14045","version":1},"attestation_state":"computed","paper":{"title":"Discovering Temporal Structure: An Overview of Hierarchical Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Akhil Bagaria, Doina Precup, George Konidaris, Marlos C. Machado, Martin Klissarov, Ziyan Luo","submitted_at":"2025-06-16T22:36:32Z","abstract_excerpt":"Developing agents capable of exploring, planning and learning in complex open-ended environments is a grand challenge in artificial intelligence (AI). Hierarchical reinforcement learning (HRL) offers a promising solution to this challenge by discovering and exploiting the temporal structure within a stream of experience. The strong appeal of the HRL framework has led to a rich and diverse body of literature attempting to discover a useful structure. However, it is still not clear how one might define what constitutes good structure in the first place, or the kind of problems in which identifyi"},"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":"2506.14045","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-16T22:36:32Z","cross_cats_sorted":[],"title_canon_sha256":"44a2ce45207933fe1206470cac0c9796d2a8e84608ac1ba5031b3a880cd55246","abstract_canon_sha256":"b71256e9c8c70da96c4cdcbf5b333881b25e1181fbb467b03903ddeef35a819b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:48.056105Z","signature_b64":"Bl661KesDYmObPXRRX1JSIQroTGY+x9MdxxBMlL23n4gv+vBk4jj7JXbqILVIyfVosdyXO59yLBItDif+297CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a999252f4619dd499724ba0c6e5744b5409ab9a07af0919ee1574becc7f213a9","last_reissued_at":"2026-07-05T11:22:48.055606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:48.055606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discovering Temporal Structure: An Overview of Hierarchical Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Akhil Bagaria, Doina Precup, George Konidaris, Marlos C. Machado, Martin Klissarov, Ziyan Luo","submitted_at":"2025-06-16T22:36:32Z","abstract_excerpt":"Developing agents capable of exploring, planning and learning in complex open-ended environments is a grand challenge in artificial intelligence (AI). Hierarchical reinforcement learning (HRL) offers a promising solution to this challenge by discovering and exploiting the temporal structure within a stream of experience. The strong appeal of the HRL framework has led to a rich and diverse body of literature attempting to discover a useful structure. However, it is still not clear how one might define what constitutes good structure in the first place, or the kind of problems in which identifyi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14045","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/2506.14045/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":"2506.14045","created_at":"2026-07-05T11:22:48.055669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14045v1","created_at":"2026-07-05T11:22:48.055669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14045","created_at":"2026-07-05T11:22:48.055669+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGMSKL2GDHOU","created_at":"2026-07-05T11:22:48.055669+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGMSKL2GDHOUTFZE","created_at":"2026-07-05T11:22:48.055669+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGMSKL2G","created_at":"2026-07-05T11:22:48.055669+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26333","citing_title":"Mesh-RL: Coupled subgrid reinforcement learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10705","citing_title":"Event-Driven Reinforcement Learning Enables Long-Horizon Control in Semiconductor Fabrication","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20622","citing_title":"Darwin Mobile Agent: A Roadmap for Self-Evolution","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23551","citing_title":"Goal-Conditioned Agents that Learn Everything All at Once","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13207","citing_title":"Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24558","citing_title":"Hierarchical Behaviour Spaces","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VGMSKL2GDHOUTFZEXIGG4V2EWV","json":"https://pith.science/pith/VGMSKL2GDHOUTFZEXIGG4V2EWV.json","graph_json":"https://pith.science/api/pith-number/VGMSKL2GDHOUTFZEXIGG4V2EWV/graph.json","events_json":"https://pith.science/api/pith-number/VGMSKL2GDHOUTFZEXIGG4V2EWV/events.json","paper":"https://pith.science/paper/VGMSKL2G"},"agent_actions":{"view_html":"https://pith.science/pith/VGMSKL2GDHOUTFZEXIGG4V2EWV","download_json":"https://pith.science/pith/VGMSKL2GDHOUTFZEXIGG4V2EWV.json","view_paper":"https://pith.science/paper/VGMSKL2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14045&json=true","fetch_graph":"https://pith.science/api/pith-number/VGMSKL2GDHOUTFZEXIGG4V2EWV/graph.json","fetch_events":"https://pith.science/api/pith-number/VGMSKL2GDHOUTFZEXIGG4V2EWV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGMSKL2GDHOUTFZEXIGG4V2EWV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGMSKL2GDHOUTFZEXIGG4V2EWV/action/storage_attestation","attest_author":"https://pith.science/pith/VGMSKL2GDHOUTFZEXIGG4V2EWV/action/author_attestation","sign_citation":"https://pith.science/pith/VGMSKL2GDHOUTFZEXIGG4V2EWV/action/citation_signature","submit_replication":"https://pith.science/pith/VGMSKL2GDHOUTFZEXIGG4V2EWV/action/replication_record"}},"created_at":"2026-07-05T11:22:48.055669+00:00","updated_at":"2026-07-05T11:22:48.055669+00:00"}