{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WEZNAEZKNBYFJ7YSL7XC2TIAF7","short_pith_number":"pith:WEZNAEZK","canonical_record":{"source":{"id":"2102.02274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-03T20:10:23Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"01d95ede9c7681b759eea7be09109280f536423acd1f436405804d148be922c6","abstract_canon_sha256":"597d2d14e52c6e72ebb0e36dd8206cb7bb03f77c6c770f5d8bc2fa88ec4e3651"},"schema_version":"1.0"},"canonical_sha256":"b132d0132a687054ff125fee2d4d002fed21bd5884503d5bf63418f9a50dfa4d","source":{"kind":"arxiv","id":"2102.02274","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.02274","created_at":"2026-07-05T02:12:46Z"},{"alias_kind":"arxiv_version","alias_value":"2102.02274v1","created_at":"2026-07-05T02:12:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02274","created_at":"2026-07-05T02:12:46Z"},{"alias_kind":"pith_short_12","alias_value":"WEZNAEZKNBYF","created_at":"2026-07-05T02:12:46Z"},{"alias_kind":"pith_short_16","alias_value":"WEZNAEZKNBYFJ7YS","created_at":"2026-07-05T02:12:46Z"},{"alias_kind":"pith_short_8","alias_value":"WEZNAEZK","created_at":"2026-07-05T02:12:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WEZNAEZKNBYFJ7YSL7XC2TIAF7","target":"record","payload":{"canonical_record":{"source":{"id":"2102.02274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-03T20:10:23Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"01d95ede9c7681b759eea7be09109280f536423acd1f436405804d148be922c6","abstract_canon_sha256":"597d2d14e52c6e72ebb0e36dd8206cb7bb03f77c6c770f5d8bc2fa88ec4e3651"},"schema_version":"1.0"},"canonical_sha256":"b132d0132a687054ff125fee2d4d002fed21bd5884503d5bf63418f9a50dfa4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:12:46.616964Z","signature_b64":"pQgtd5Kqx8EV9j7CQB97GuCVeB/lyBiNaLTVZms4j5WKCEQuZMs8JbTzQQx+PBCbNwJSy8z8GsaqKtm8F7zLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b132d0132a687054ff125fee2d4d002fed21bd5884503d5bf63418f9a50dfa4d","last_reissued_at":"2026-07-05T02:12:46.616539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:12:46.616539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.02274","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:12:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EVYkccctmGVyg26SEDYqEPkXUyNQ/xbzeuD56UeNWVkwjvIvAu+5Zs34MhN50Zixes4OuihsZ8iR1XPeskraDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:08:07.180490Z"},"content_sha256":"de3095f1896f295ed3c0058f3729ff3a0825bee646028b306b7af16cc4c58e41","schema_version":"1.0","event_id":"sha256:de3095f1896f295ed3c0058f3729ff3a0825bee646028b306b7af16cc4c58e41"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WEZNAEZKNBYFJ7YSL7XC2TIAF7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Recursive Belief States in Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Bernardo Avila Pires, Edward Hughes, Kevin R. McKee, Pol Moreno, Th\\'eophane Weber","submitted_at":"2021-02-03T20:10:23Z","abstract_excerpt":"In multi-agent reinforcement learning, the problem of learning to act is particularly difficult because the policies of co-players may be heavily conditioned on information only observed by them. On the other hand, humans readily form beliefs about the knowledge possessed by their peers and leverage beliefs to inform decision-making. Such abilities underlie individual success in a wide range of Markov games, from bluffing in Poker to conditional cooperation in the Prisoner's Dilemma, to convention-building in Bridge. Classical methods are usually not applicable to complex domains due to the in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02274","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/2102.02274/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:12:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IZERaKMT9JYNWO6JOm/jjdCOMF1jMOukKKS2tjtyOHThXYdoWdR20g8jEA14QE6gkTigfkjwGkCYXu5g+7lSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:08:07.181339Z"},"content_sha256":"2d30887d9d26c9d30c31b7149b04f70a380dd9c08538334552da504d1bd5026e","schema_version":"1.0","event_id":"sha256:2d30887d9d26c9d30c31b7149b04f70a380dd9c08538334552da504d1bd5026e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WEZNAEZKNBYFJ7YSL7XC2TIAF7/bundle.json","state_url":"https://pith.science/pith/WEZNAEZKNBYFJ7YSL7XC2TIAF7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WEZNAEZKNBYFJ7YSL7XC2TIAF7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T14:08:07Z","links":{"resolver":"https://pith.science/pith/WEZNAEZKNBYFJ7YSL7XC2TIAF7","bundle":"https://pith.science/pith/WEZNAEZKNBYFJ7YSL7XC2TIAF7/bundle.json","state":"https://pith.science/pith/WEZNAEZKNBYFJ7YSL7XC2TIAF7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WEZNAEZKNBYFJ7YSL7XC2TIAF7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WEZNAEZKNBYFJ7YSL7XC2TIAF7","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":"597d2d14e52c6e72ebb0e36dd8206cb7bb03f77c6c770f5d8bc2fa88ec4e3651","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-03T20:10:23Z","title_canon_sha256":"01d95ede9c7681b759eea7be09109280f536423acd1f436405804d148be922c6"},"schema_version":"1.0","source":{"id":"2102.02274","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.02274","created_at":"2026-07-05T02:12:46Z"},{"alias_kind":"arxiv_version","alias_value":"2102.02274v1","created_at":"2026-07-05T02:12:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02274","created_at":"2026-07-05T02:12:46Z"},{"alias_kind":"pith_short_12","alias_value":"WEZNAEZKNBYF","created_at":"2026-07-05T02:12:46Z"},{"alias_kind":"pith_short_16","alias_value":"WEZNAEZKNBYFJ7YS","created_at":"2026-07-05T02:12:46Z"},{"alias_kind":"pith_short_8","alias_value":"WEZNAEZK","created_at":"2026-07-05T02:12:46Z"}],"graph_snapshots":[{"event_id":"sha256:2d30887d9d26c9d30c31b7149b04f70a380dd9c08538334552da504d1bd5026e","target":"graph","created_at":"2026-07-05T02:12:46Z","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/2102.02274/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In multi-agent reinforcement learning, the problem of learning to act is particularly difficult because the policies of co-players may be heavily conditioned on information only observed by them. On the other hand, humans readily form beliefs about the knowledge possessed by their peers and leverage beliefs to inform decision-making. Such abilities underlie individual success in a wide range of Markov games, from bluffing in Poker to conditional cooperation in the Prisoner's Dilemma, to convention-building in Bridge. Classical methods are usually not applicable to complex domains due to the in","authors_text":"Bernardo Avila Pires, Edward Hughes, Kevin R. McKee, Pol Moreno, Th\\'eophane Weber","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-03T20:10:23Z","title":"Neural Recursive Belief States in Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02274","kind":"arxiv","version":1},"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:de3095f1896f295ed3c0058f3729ff3a0825bee646028b306b7af16cc4c58e41","target":"record","created_at":"2026-07-05T02:12:46Z","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":"597d2d14e52c6e72ebb0e36dd8206cb7bb03f77c6c770f5d8bc2fa88ec4e3651","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-03T20:10:23Z","title_canon_sha256":"01d95ede9c7681b759eea7be09109280f536423acd1f436405804d148be922c6"},"schema_version":"1.0","source":{"id":"2102.02274","kind":"arxiv","version":1}},"canonical_sha256":"b132d0132a687054ff125fee2d4d002fed21bd5884503d5bf63418f9a50dfa4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b132d0132a687054ff125fee2d4d002fed21bd5884503d5bf63418f9a50dfa4d","first_computed_at":"2026-07-05T02:12:46.616539Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:12:46.616539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pQgtd5Kqx8EV9j7CQB97GuCVeB/lyBiNaLTVZms4j5WKCEQuZMs8JbTzQQx+PBCbNwJSy8z8GsaqKtm8F7zLCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:12:46.616964Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.02274","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de3095f1896f295ed3c0058f3729ff3a0825bee646028b306b7af16cc4c58e41","sha256:2d30887d9d26c9d30c31b7149b04f70a380dd9c08538334552da504d1bd5026e"],"state_sha256":"d862cb9af133070cd996049345ab24d48105fc0af5ac38a37d240b862c5668ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dxF2fRYeERRwWFUp3zdkxr9mBkWbt/hxLbdzLd3DEwgdh2PH4Ae/VeI8ihPNk54Cfirr4O7XLCFHTexTijoPBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:08:07.200277Z","bundle_sha256":"b9770bc1623fa70ed769457c4a763d3ecf1062a4817c3b342db82956a73df457"}}