{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BCHAB3RIRECIJL47SAHWTWOBIK","short_pith_number":"pith:BCHAB3RI","schema_version":"1.0","canonical_sha256":"088e00ee28890484af9f900f69d9c1428605906720c3cbcdd6bdf82d317ed793","source":{"kind":"arxiv","id":"2006.04222","version":3},"attestation_state":"computed","paper":{"title":"Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bei Peng, Christian A. Schroeder de Witt, Fei Sha, Shariq Iqbal, Shimon Whiteson, Wendelin B\\\"ohmer","submitted_at":"2020-06-07T18:28:41Z","abstract_excerpt":"Multi-agent settings in the real world often involve tasks with varying types and quantities of agents and non-agent entities; however, common patterns of behavior often emerge among these agents/entities. Our method aims to leverage these commonalities by asking the question: ``What is the expected utility of each agent when only considering a randomly selected sub-group of its observed entities?'' By posing this counterfactual question, we can recognize state-action trajectories within sub-groups of entities that we may have encountered in another task and use what we learned in that task to"},"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":"2006.04222","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-07T18:28:41Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"075d7aa0ec559459ad6031c2a27e7e73a9e82549657fda1d0cfe84c0320fc5f6","abstract_canon_sha256":"979a19ae5dd2343563883cc8c8fdaa294e15f43192e1dfcc94279ded168024f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:33.335184Z","signature_b64":"Clklcm46jv+fbF5plsYBI3PXHiduVRsnISe2Or6+2EbrEL7rujhOsP6kRzf9UhGEXnS0RPURmqdxBNdprAElBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"088e00ee28890484af9f900f69d9c1428605906720c3cbcdd6bdf82d317ed793","last_reissued_at":"2026-07-05T02:48:33.334699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:33.334699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bei Peng, Christian A. Schroeder de Witt, Fei Sha, Shariq Iqbal, Shimon Whiteson, Wendelin B\\\"ohmer","submitted_at":"2020-06-07T18:28:41Z","abstract_excerpt":"Multi-agent settings in the real world often involve tasks with varying types and quantities of agents and non-agent entities; however, common patterns of behavior often emerge among these agents/entities. Our method aims to leverage these commonalities by asking the question: ``What is the expected utility of each agent when only considering a randomly selected sub-group of its observed entities?'' By posing this counterfactual question, we can recognize state-action trajectories within sub-groups of entities that we may have encountered in another task and use what we learned in that task to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.04222","kind":"arxiv","version":3},"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/2006.04222/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":"2006.04222","created_at":"2026-07-05T02:48:33.334763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.04222v3","created_at":"2026-07-05T02:48:33.334763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04222","created_at":"2026-07-05T02:48:33.334763+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCHAB3RIRECI","created_at":"2026-07-05T02:48:33.334763+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCHAB3RIRECIJL47","created_at":"2026-07-05T02:48:33.334763+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCHAB3RI","created_at":"2026-07-05T02:48:33.334763+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20039","citing_title":"Learning Bilateral Team Formation in Cooperative Multi-Agent Reinforcement Learning","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BCHAB3RIRECIJL47SAHWTWOBIK","json":"https://pith.science/pith/BCHAB3RIRECIJL47SAHWTWOBIK.json","graph_json":"https://pith.science/api/pith-number/BCHAB3RIRECIJL47SAHWTWOBIK/graph.json","events_json":"https://pith.science/api/pith-number/BCHAB3RIRECIJL47SAHWTWOBIK/events.json","paper":"https://pith.science/paper/BCHAB3RI"},"agent_actions":{"view_html":"https://pith.science/pith/BCHAB3RIRECIJL47SAHWTWOBIK","download_json":"https://pith.science/pith/BCHAB3RIRECIJL47SAHWTWOBIK.json","view_paper":"https://pith.science/paper/BCHAB3RI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.04222&json=true","fetch_graph":"https://pith.science/api/pith-number/BCHAB3RIRECIJL47SAHWTWOBIK/graph.json","fetch_events":"https://pith.science/api/pith-number/BCHAB3RIRECIJL47SAHWTWOBIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCHAB3RIRECIJL47SAHWTWOBIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCHAB3RIRECIJL47SAHWTWOBIK/action/storage_attestation","attest_author":"https://pith.science/pith/BCHAB3RIRECIJL47SAHWTWOBIK/action/author_attestation","sign_citation":"https://pith.science/pith/BCHAB3RIRECIJL47SAHWTWOBIK/action/citation_signature","submit_replication":"https://pith.science/pith/BCHAB3RIRECIJL47SAHWTWOBIK/action/replication_record"}},"created_at":"2026-07-05T02:48:33.334763+00:00","updated_at":"2026-07-05T02:48:33.334763+00:00"}