{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DXH2JS3IC6H67ALNCKRB2X22JZ","short_pith_number":"pith:DXH2JS3I","schema_version":"1.0","canonical_sha256":"1dcfa4cb68178fef816d12a21d5f5a4e66ed7f126dffca7342ce200448fc6db3","source":{"kind":"arxiv","id":"2403.01816","version":1},"attestation_state":"computed","paper":{"title":"SMAUG: A Sliding Multidimensional Task Window-Based MARL Framework for Adaptive Real-Time Subtask Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Wei Zhang, Wenjing Zhang","submitted_at":"2024-03-04T08:04:41Z","abstract_excerpt":"Instead of making behavioral decisions directly from the exponentially expanding joint observational-action space, subtask-based multi-agent reinforcement learning (MARL) methods enable agents to learn how to tackle different subtasks. Most existing subtask-based MARL methods are based on hierarchical reinforcement learning (HRL). However, these approaches often limit the number of subtasks, perform subtask recognition periodically, and can only identify and execute a specific subtask within the predefined fixed time period, which makes them inflexible and not suitable for diverse and dynamic "},"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":"2403.01816","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-04T08:04:41Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"5ab4f8d7f6cb3b082c358d8b25b6748ec39e4d8e005c20707ca8e8894fecb98e","abstract_canon_sha256":"0213df7aaacee4de0dc6696339e0469cc59eca909bfc122ec0273c1671ff82ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:52.293841Z","signature_b64":"uP97Vr7AolaXyg0jlb9H1FlR9KEbZkdstyf/35NaMqRjo3dGCIrZ/Z45RUaNU3M7SMPC6LebPbOPXyHV6Kc7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dcfa4cb68178fef816d12a21d5f5a4e66ed7f126dffca7342ce200448fc6db3","last_reissued_at":"2026-07-05T07:51:52.293287Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:52.293287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMAUG: A Sliding Multidimensional Task Window-Based MARL Framework for Adaptive Real-Time Subtask Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Wei Zhang, Wenjing Zhang","submitted_at":"2024-03-04T08:04:41Z","abstract_excerpt":"Instead of making behavioral decisions directly from the exponentially expanding joint observational-action space, subtask-based multi-agent reinforcement learning (MARL) methods enable agents to learn how to tackle different subtasks. Most existing subtask-based MARL methods are based on hierarchical reinforcement learning (HRL). However, these approaches often limit the number of subtasks, perform subtask recognition periodically, and can only identify and execute a specific subtask within the predefined fixed time period, which makes them inflexible and not suitable for diverse and dynamic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01816","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/2403.01816/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":"2403.01816","created_at":"2026-07-05T07:51:52.293358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.01816v1","created_at":"2026-07-05T07:51:52.293358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01816","created_at":"2026-07-05T07:51:52.293358+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXH2JS3IC6H6","created_at":"2026-07-05T07:51:52.293358+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXH2JS3IC6H67ALN","created_at":"2026-07-05T07:51:52.293358+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXH2JS3I","created_at":"2026-07-05T07:51:52.293358+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06901","citing_title":"Designing Adaptive Algorithms Based on Reinforcement Learning for Dynamic Optimization of Sliding Window Size in Multi-Dimensional Data Streams","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DXH2JS3IC6H67ALNCKRB2X22JZ","json":"https://pith.science/pith/DXH2JS3IC6H67ALNCKRB2X22JZ.json","graph_json":"https://pith.science/api/pith-number/DXH2JS3IC6H67ALNCKRB2X22JZ/graph.json","events_json":"https://pith.science/api/pith-number/DXH2JS3IC6H67ALNCKRB2X22JZ/events.json","paper":"https://pith.science/paper/DXH2JS3I"},"agent_actions":{"view_html":"https://pith.science/pith/DXH2JS3IC6H67ALNCKRB2X22JZ","download_json":"https://pith.science/pith/DXH2JS3IC6H67ALNCKRB2X22JZ.json","view_paper":"https://pith.science/paper/DXH2JS3I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.01816&json=true","fetch_graph":"https://pith.science/api/pith-number/DXH2JS3IC6H67ALNCKRB2X22JZ/graph.json","fetch_events":"https://pith.science/api/pith-number/DXH2JS3IC6H67ALNCKRB2X22JZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXH2JS3IC6H67ALNCKRB2X22JZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXH2JS3IC6H67ALNCKRB2X22JZ/action/storage_attestation","attest_author":"https://pith.science/pith/DXH2JS3IC6H67ALNCKRB2X22JZ/action/author_attestation","sign_citation":"https://pith.science/pith/DXH2JS3IC6H67ALNCKRB2X22JZ/action/citation_signature","submit_replication":"https://pith.science/pith/DXH2JS3IC6H67ALNCKRB2X22JZ/action/replication_record"}},"created_at":"2026-07-05T07:51:52.293358+00:00","updated_at":"2026-07-05T07:51:52.293358+00:00"}