{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:OUVDML6TVCGAIIOGPH2IJL5IWU","short_pith_number":"pith:OUVDML6T","canonical_record":{"source":{"id":"1906.01470","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-04T14:18:47Z","cross_cats_sorted":["cs.AI","cs.MA","cs.NE","stat.ML"],"title_canon_sha256":"6c619b8e1d12c64443a7311df4b3a156ab19a398663baedc34e6771dba3701f7","abstract_canon_sha256":"649853f8db6cbf5f72080f82daa36ffa2e4ec0582f7ad83a26acc14e8304d63f"},"schema_version":"1.0"},"canonical_sha256":"752a362fd3a88c0421c679f484afa8b500fcad465009993f09b535062b87ea59","source":{"kind":"arxiv","id":"1906.01470","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.01470","created_at":"2026-07-05T01:17:37Z"},{"alias_kind":"arxiv_version","alias_value":"1906.01470v3","created_at":"2026-07-05T01:17:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01470","created_at":"2026-07-05T01:17:37Z"},{"alias_kind":"pith_short_12","alias_value":"OUVDML6TVCGA","created_at":"2026-07-05T01:17:37Z"},{"alias_kind":"pith_short_16","alias_value":"OUVDML6TVCGAIIOG","created_at":"2026-07-05T01:17:37Z"},{"alias_kind":"pith_short_8","alias_value":"OUVDML6T","created_at":"2026-07-05T01:17:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:OUVDML6TVCGAIIOGPH2IJL5IWU","target":"record","payload":{"canonical_record":{"source":{"id":"1906.01470","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-04T14:18:47Z","cross_cats_sorted":["cs.AI","cs.MA","cs.NE","stat.ML"],"title_canon_sha256":"6c619b8e1d12c64443a7311df4b3a156ab19a398663baedc34e6771dba3701f7","abstract_canon_sha256":"649853f8db6cbf5f72080f82daa36ffa2e4ec0582f7ad83a26acc14e8304d63f"},"schema_version":"1.0"},"canonical_sha256":"752a362fd3a88c0421c679f484afa8b500fcad465009993f09b535062b87ea59","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:37.698016Z","signature_b64":"GJlJ+vmpTSnGYNwZQMR7Pfu/RjerVVb7zn1+yV0BI/hrj8Nv1+kqaIHfQDeeVWBIDUx36lkzRVWEqbPcmK0CCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"752a362fd3a88c0421c679f484afa8b500fcad465009993f09b535062b87ea59","last_reissued_at":"2026-07-05T01:17:37.697467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:37.697467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.01470","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:17:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"znsqifSLB/kn8Mm1ahNnXDixrv+dKYxTB5HVUcsH3uHuBslYkr/9cd1dzbCHoTDvvIsZ1ZP0PRzef8z+3jrGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:28:18.532290Z"},"content_sha256":"5f97c25029ac84a1ea8d116fee8d94f1d20c0a3d755c695a2c020179aa2acdea","schema_version":"1.0","event_id":"sha256:5f97c25029ac84a1ea8d116fee8d94f1d20c0a3d755c695a2c020179aa2acdea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:OUVDML6TVCGAIIOGPH2IJL5IWU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Options as responses: Grounding behavioural hierarchies in multi-agent RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Sasha Vezhnevets, Joel Z. Leibo, Remi Leblond, Yuhuai Wu","submitted_at":"2019-06-04T14:18:47Z","abstract_excerpt":"This paper investigates generalisation in multi-agent games, where the generality of the agent can be evaluated by playing against opponents it hasn't seen during training. We propose two new games with concealed information and complex, non-transitive reward structure (think rock/paper/scissors). It turns out that most current deep reinforcement learning methods fail to efficiently explore the strategy space, thus learning policies that generalise poorly to unseen opponents. We then propose a novel hierarchical agent architecture, where the hierarchy is grounded in the game-theoretic structur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01470","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/1906.01470/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":"2026-07-05T01:17:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dOr5TmB6hoXBK9DZsbtQ4aQoxgSIkvUH+0IFGEioAyzOfK2uwxCfgqagXvoj7Olv9bBCjShfKD8DFyfDyVqWBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:28:18.532669Z"},"content_sha256":"711d8726f635418ff43576b1025093c452f7dd08e4a6736b2a87b2c671270db1","schema_version":"1.0","event_id":"sha256:711d8726f635418ff43576b1025093c452f7dd08e4a6736b2a87b2c671270db1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OUVDML6TVCGAIIOGPH2IJL5IWU/bundle.json","state_url":"https://pith.science/pith/OUVDML6TVCGAIIOGPH2IJL5IWU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OUVDML6TVCGAIIOGPH2IJL5IWU/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":"2026-08-11T21:28:18Z","links":{"resolver":"https://pith.science/pith/OUVDML6TVCGAIIOGPH2IJL5IWU","bundle":"https://pith.science/pith/OUVDML6TVCGAIIOGPH2IJL5IWU/bundle.json","state":"https://pith.science/pith/OUVDML6TVCGAIIOGPH2IJL5IWU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OUVDML6TVCGAIIOGPH2IJL5IWU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:OUVDML6TVCGAIIOGPH2IJL5IWU","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":"649853f8db6cbf5f72080f82daa36ffa2e4ec0582f7ad83a26acc14e8304d63f","cross_cats_sorted":["cs.AI","cs.MA","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-04T14:18:47Z","title_canon_sha256":"6c619b8e1d12c64443a7311df4b3a156ab19a398663baedc34e6771dba3701f7"},"schema_version":"1.0","source":{"id":"1906.01470","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.01470","created_at":"2026-07-05T01:17:37Z"},{"alias_kind":"arxiv_version","alias_value":"1906.01470v3","created_at":"2026-07-05T01:17:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01470","created_at":"2026-07-05T01:17:37Z"},{"alias_kind":"pith_short_12","alias_value":"OUVDML6TVCGA","created_at":"2026-07-05T01:17:37Z"},{"alias_kind":"pith_short_16","alias_value":"OUVDML6TVCGAIIOG","created_at":"2026-07-05T01:17:37Z"},{"alias_kind":"pith_short_8","alias_value":"OUVDML6T","created_at":"2026-07-05T01:17:37Z"}],"graph_snapshots":[{"event_id":"sha256:711d8726f635418ff43576b1025093c452f7dd08e4a6736b2a87b2c671270db1","target":"graph","created_at":"2026-07-05T01:17:37Z","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/1906.01470/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates generalisation in multi-agent games, where the generality of the agent can be evaluated by playing against opponents it hasn't seen during training. We propose two new games with concealed information and complex, non-transitive reward structure (think rock/paper/scissors). It turns out that most current deep reinforcement learning methods fail to efficiently explore the strategy space, thus learning policies that generalise poorly to unseen opponents. We then propose a novel hierarchical agent architecture, where the hierarchy is grounded in the game-theoretic structur","authors_text":"Alexander Sasha Vezhnevets, Joel Z. Leibo, Remi Leblond, Yuhuai Wu","cross_cats":["cs.AI","cs.MA","cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-04T14:18:47Z","title":"Options as responses: Grounding behavioural hierarchies in multi-agent RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01470","kind":"arxiv","version":3},"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":"sha256:5f97c25029ac84a1ea8d116fee8d94f1d20c0a3d755c695a2c020179aa2acdea","target":"record","created_at":"2026-07-05T01:17:37Z","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":"649853f8db6cbf5f72080f82daa36ffa2e4ec0582f7ad83a26acc14e8304d63f","cross_cats_sorted":["cs.AI","cs.MA","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-04T14:18:47Z","title_canon_sha256":"6c619b8e1d12c64443a7311df4b3a156ab19a398663baedc34e6771dba3701f7"},"schema_version":"1.0","source":{"id":"1906.01470","kind":"arxiv","version":3}},"canonical_sha256":"752a362fd3a88c0421c679f484afa8b500fcad465009993f09b535062b87ea59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"752a362fd3a88c0421c679f484afa8b500fcad465009993f09b535062b87ea59","first_computed_at":"2026-07-05T01:17:37.697467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:17:37.697467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GJlJ+vmpTSnGYNwZQMR7Pfu/RjerVVb7zn1+yV0BI/hrj8Nv1+kqaIHfQDeeVWBIDUx36lkzRVWEqbPcmK0CCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:17:37.698016Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.01470","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f97c25029ac84a1ea8d116fee8d94f1d20c0a3d755c695a2c020179aa2acdea","sha256:711d8726f635418ff43576b1025093c452f7dd08e4a6736b2a87b2c671270db1"],"state_sha256":"c2dfcd27277e1eb1a6f2d6ac2b25fdd11172b28d400ee29f56ff87055cef8db2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1a+7PvhDHyvoFVlrvBMKrSUBxMzsYuOClchLYLqrl66USnVgwRl9NwYuQ0QLawRiQ03ulfbP5h3ViuViBfbFAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T21:28:18.535287Z","bundle_sha256":"b6a12f39bba3d3bd9412018a9c20201bef5ebb9283922fb75a38c2c3b006e090"}}