{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:45HYHW4AQBS4LZTQZBY4GIEWX7","short_pith_number":"pith:45HYHW4A","schema_version":"1.0","canonical_sha256":"e74f83db808065c5e670c871c32096bff8450c49799e5cd734f1606587995cf4","source":{"kind":"arxiv","id":"2206.12765","version":1},"attestation_state":"computed","paper":{"title":"Generalized Beliefs for Cooperative AI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Christian Schroeder de Witt, Darius Muglich, Jakob Foerster, Luisa Zintgraf, Shimon Whiteson","submitted_at":"2022-06-26T02:13:40Z","abstract_excerpt":"Self-play is a common paradigm for constructing solutions in Markov games that can yield optimal policies in collaborative settings. However, these policies often adopt highly-specialized conventions that make playing with a novel partner difficult. To address this, recent approaches rely on encoding symmetry and convention-awareness into policy training, but these require strong environmental assumptions and can complicate policy training. We therefore propose moving the learning of conventions to the belief space. Specifically, we propose a belief learning model that can maintain beliefs ove"},"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":"2206.12765","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-06-26T02:13:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3db79d2d3e881835e1c70ba7f1384c85066b5105d4504adfc8401258a7efb25b","abstract_canon_sha256":"5293e768a1ec85f506811d76bcd12c1cc8bddcfb39b768c7df8ae1d74ed39dba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:59.048588Z","signature_b64":"+UI7J1NckeFb8psZuwCWxPVCeNqqiE21oKMEocpJ3RtwDO45QePpQIp51eBfG1ojeOzXJ0GNlZczqAfdhfw7Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e74f83db808065c5e670c871c32096bff8450c49799e5cd734f1606587995cf4","last_reissued_at":"2026-07-05T04:34:59.048219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:59.048219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalized Beliefs for Cooperative AI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Christian Schroeder de Witt, Darius Muglich, Jakob Foerster, Luisa Zintgraf, Shimon Whiteson","submitted_at":"2022-06-26T02:13:40Z","abstract_excerpt":"Self-play is a common paradigm for constructing solutions in Markov games that can yield optimal policies in collaborative settings. However, these policies often adopt highly-specialized conventions that make playing with a novel partner difficult. To address this, recent approaches rely on encoding symmetry and convention-awareness into policy training, but these require strong environmental assumptions and can complicate policy training. We therefore propose moving the learning of conventions to the belief space. Specifically, we propose a belief learning model that can maintain beliefs ove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.12765","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/2206.12765/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":"2206.12765","created_at":"2026-07-05T04:34:59.048275+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.12765v1","created_at":"2026-07-05T04:34:59.048275+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.12765","created_at":"2026-07-05T04:34:59.048275+00:00"},{"alias_kind":"pith_short_12","alias_value":"45HYHW4AQBS4","created_at":"2026-07-05T04:34:59.048275+00:00"},{"alias_kind":"pith_short_16","alias_value":"45HYHW4AQBS4LZTQ","created_at":"2026-07-05T04:34:59.048275+00:00"},{"alias_kind":"pith_short_8","alias_value":"45HYHW4A","created_at":"2026-07-05T04:34:59.048275+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/45HYHW4AQBS4LZTQZBY4GIEWX7","json":"https://pith.science/pith/45HYHW4AQBS4LZTQZBY4GIEWX7.json","graph_json":"https://pith.science/api/pith-number/45HYHW4AQBS4LZTQZBY4GIEWX7/graph.json","events_json":"https://pith.science/api/pith-number/45HYHW4AQBS4LZTQZBY4GIEWX7/events.json","paper":"https://pith.science/paper/45HYHW4A"},"agent_actions":{"view_html":"https://pith.science/pith/45HYHW4AQBS4LZTQZBY4GIEWX7","download_json":"https://pith.science/pith/45HYHW4AQBS4LZTQZBY4GIEWX7.json","view_paper":"https://pith.science/paper/45HYHW4A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.12765&json=true","fetch_graph":"https://pith.science/api/pith-number/45HYHW4AQBS4LZTQZBY4GIEWX7/graph.json","fetch_events":"https://pith.science/api/pith-number/45HYHW4AQBS4LZTQZBY4GIEWX7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/45HYHW4AQBS4LZTQZBY4GIEWX7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/45HYHW4AQBS4LZTQZBY4GIEWX7/action/storage_attestation","attest_author":"https://pith.science/pith/45HYHW4AQBS4LZTQZBY4GIEWX7/action/author_attestation","sign_citation":"https://pith.science/pith/45HYHW4AQBS4LZTQZBY4GIEWX7/action/citation_signature","submit_replication":"https://pith.science/pith/45HYHW4AQBS4LZTQZBY4GIEWX7/action/replication_record"}},"created_at":"2026-07-05T04:34:59.048275+00:00","updated_at":"2026-07-05T04:34:59.048275+00:00"}