{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PNEZKGLXU2I5SN2BEUB3ANF5HX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"19e105be0191632302333e0590eff616c41a34168ac8ace6e69c6575ac5dcb23","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-03-06T01:09:55Z","title_canon_sha256":"497b20b170068cff7fa1db747f9d3709cd9642508016482414562da316035878"},"schema_version":"1.0","source":{"id":"2103.04000","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.04000","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"arxiv_version","alias_value":"2103.04000v5","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.04000","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"pith_short_12","alias_value":"PNEZKGLXU2I5","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"pith_short_16","alias_value":"PNEZKGLXU2I5SN2B","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"pith_short_8","alias_value":"PNEZKGLX","created_at":"2026-07-05T03:06:46Z"}],"graph_snapshots":[{"event_id":"sha256:312ef01d6372ed35ddaf767f983983075fbc1a138e1074c9c4a910ee179911d0","target":"graph","created_at":"2026-07-05T03:06:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2103.04000/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The standard problem setting in Dec-POMDPs is self-play, where the goal is to find a set of policies that play optimally together. Policies learned through self-play may adopt arbitrary conventions and implicitly rely on multi-step reasoning based on fragile assumptions about other agents' actions and thus fail when paired with humans or independently trained agents at test time. To address this, we present off-belief learning (OBL). At each timestep OBL agents follow a policy $\\pi_1$ that is optimized assuming past actions were taken by a given, fixed policy ($\\pi_0$), but assuming that futur","authors_text":"Adam Lerer, Brandon Cui, David Wu, Hengyuan Hu, Jakob Foerster, Luis Pineda, Noam Brown","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-03-06T01:09:55Z","title":"Off-Belief Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.04000","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d2c118f0b06f5c516a69d8b8096c8ed29c03926d7ced95ceb396a06715cbaaf0","target":"record","created_at":"2026-07-05T03:06:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"19e105be0191632302333e0590eff616c41a34168ac8ace6e69c6575ac5dcb23","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-03-06T01:09:55Z","title_canon_sha256":"497b20b170068cff7fa1db747f9d3709cd9642508016482414562da316035878"},"schema_version":"1.0","source":{"id":"2103.04000","kind":"arxiv","version":5}},"canonical_sha256":"7b49951977a691d937412503b034bd3de89866a3d0831a5c94c1983ae74ac756","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b49951977a691d937412503b034bd3de89866a3d0831a5c94c1983ae74ac756","first_computed_at":"2026-07-05T03:06:46.014390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:06:46.014390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CeYOwblox38BqFI+L3t6GSdTVAnwACz9sx73lKnSYclV/R72ywhXDOvy+EfZhSyvZPx/0o+RnEFOinfDNoMHCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:06:46.014885Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.04000","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2c118f0b06f5c516a69d8b8096c8ed29c03926d7ced95ceb396a06715cbaaf0","sha256:312ef01d6372ed35ddaf767f983983075fbc1a138e1074c9c4a910ee179911d0"],"state_sha256":"8459a95808d321dbca8b74a6403b09885ddb76d1b12bb5b1b046a969f4346162"}