{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YMSR7WKIUXNEU2JOLSKMKI4P4D","short_pith_number":"pith:YMSR7WKI","schema_version":"1.0","canonical_sha256":"c3251fd948a5da4a692e5c94c5238fe0ed8e6a5bc165cb2986603de6e56a4192","source":{"kind":"arxiv","id":"2507.10251","version":1},"attestation_state":"computed","paper":{"title":"ToMacVF : Temporal Macro-action Value Factorization for Asynchronous Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Wei Zhang, Wenjing Zhang","submitted_at":"2025-07-14T13:18:13Z","abstract_excerpt":"Existing asynchronous MARL methods based on MacDec-POMDP typically construct training trajectory buffers by simply sampling limited and biased data at the endpoints of macro-actions, and directly apply conventional MARL methods on the buffers. As a result, these methods lead to an incomplete and inaccurate representation of the macro-action execution process, along with unsuitable credit assignments. To solve these problems, the Temporal Macro-action Value Factorization (ToMacVF) is proposed to achieve fine-grained temporal credit assignment for macro-action contributions. A centralized traini"},"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":"2507.10251","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-07-14T13:18:13Z","cross_cats_sorted":[],"title_canon_sha256":"d60087215d2ce927ad4820ddf7c2157f2f93b4dc014ff2e7afdf736488badaa1","abstract_canon_sha256":"feda25180d5e693e88da83b9fefaf7c866614a6dafbfa81b41c6313e2f1b1c06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:47.852895Z","signature_b64":"VLA0hwarvdIv3/LblwkrvodMOjUnb5z2im+n/UUa4UBPGDAxpV+IRYRnLqxakMQNqlmJke8M2TaXaIae9vNkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3251fd948a5da4a692e5c94c5238fe0ed8e6a5bc165cb2986603de6e56a4192","last_reissued_at":"2026-07-05T11:36:47.852355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:47.852355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ToMacVF : Temporal Macro-action Value Factorization for Asynchronous Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Wei Zhang, Wenjing Zhang","submitted_at":"2025-07-14T13:18:13Z","abstract_excerpt":"Existing asynchronous MARL methods based on MacDec-POMDP typically construct training trajectory buffers by simply sampling limited and biased data at the endpoints of macro-actions, and directly apply conventional MARL methods on the buffers. As a result, these methods lead to an incomplete and inaccurate representation of the macro-action execution process, along with unsuitable credit assignments. To solve these problems, the Temporal Macro-action Value Factorization (ToMacVF) is proposed to achieve fine-grained temporal credit assignment for macro-action contributions. A centralized traini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10251","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/2507.10251/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":"2507.10251","created_at":"2026-07-05T11:36:47.852413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10251v1","created_at":"2026-07-05T11:36:47.852413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10251","created_at":"2026-07-05T11:36:47.852413+00:00"},{"alias_kind":"pith_short_12","alias_value":"YMSR7WKIUXNE","created_at":"2026-07-05T11:36:47.852413+00:00"},{"alias_kind":"pith_short_16","alias_value":"YMSR7WKIUXNEU2JO","created_at":"2026-07-05T11:36:47.852413+00:00"},{"alias_kind":"pith_short_8","alias_value":"YMSR7WKI","created_at":"2026-07-05T11:36:47.852413+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YMSR7WKIUXNEU2JOLSKMKI4P4D","json":"https://pith.science/pith/YMSR7WKIUXNEU2JOLSKMKI4P4D.json","graph_json":"https://pith.science/api/pith-number/YMSR7WKIUXNEU2JOLSKMKI4P4D/graph.json","events_json":"https://pith.science/api/pith-number/YMSR7WKIUXNEU2JOLSKMKI4P4D/events.json","paper":"https://pith.science/paper/YMSR7WKI"},"agent_actions":{"view_html":"https://pith.science/pith/YMSR7WKIUXNEU2JOLSKMKI4P4D","download_json":"https://pith.science/pith/YMSR7WKIUXNEU2JOLSKMKI4P4D.json","view_paper":"https://pith.science/paper/YMSR7WKI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10251&json=true","fetch_graph":"https://pith.science/api/pith-number/YMSR7WKIUXNEU2JOLSKMKI4P4D/graph.json","fetch_events":"https://pith.science/api/pith-number/YMSR7WKIUXNEU2JOLSKMKI4P4D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YMSR7WKIUXNEU2JOLSKMKI4P4D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YMSR7WKIUXNEU2JOLSKMKI4P4D/action/storage_attestation","attest_author":"https://pith.science/pith/YMSR7WKIUXNEU2JOLSKMKI4P4D/action/author_attestation","sign_citation":"https://pith.science/pith/YMSR7WKIUXNEU2JOLSKMKI4P4D/action/citation_signature","submit_replication":"https://pith.science/pith/YMSR7WKIUXNEU2JOLSKMKI4P4D/action/replication_record"}},"created_at":"2026-07-05T11:36:47.852413+00:00","updated_at":"2026-07-05T11:36:47.852413+00:00"}