{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:6DTDNU2OFBHPUPIMFEBNNVXJ3A","short_pith_number":"pith:6DTDNU2O","canonical_record":{"source":{"id":"1905.13428","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T06:02:52Z","cross_cats_sorted":["cs.MA","cs.SY","stat.ML"],"title_canon_sha256":"3b9ca0edfe7e6739ba1938c00456be91ea15c3567f8e02089eb4dded8c376cc5","abstract_canon_sha256":"61285761945103766d6a3e07ba643659bbddbdefed879b761a76d0dcf98bee7c"},"schema_version":"1.0"},"canonical_sha256":"f0e636d34e284efa3d0c2902d6d6e9d83e8b8b064845c771dcfa95134ae8965d","source":{"kind":"arxiv","id":"1905.13428","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.13428","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"arxiv_version","alias_value":"1905.13428v1","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13428","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"pith_short_12","alias_value":"6DTDNU2OFBHP","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6DTDNU2OFBHPUPIM","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6DTDNU2O","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:6DTDNU2OFBHPUPIMFEBNNVXJ3A","target":"record","payload":{"canonical_record":{"source":{"id":"1905.13428","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T06:02:52Z","cross_cats_sorted":["cs.MA","cs.SY","stat.ML"],"title_canon_sha256":"3b9ca0edfe7e6739ba1938c00456be91ea15c3567f8e02089eb4dded8c376cc5","abstract_canon_sha256":"61285761945103766d6a3e07ba643659bbddbdefed879b761a76d0dcf98bee7c"},"schema_version":"1.0"},"canonical_sha256":"f0e636d34e284efa3d0c2902d6d6e9d83e8b8b064845c771dcfa95134ae8965d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:34.931449Z","signature_b64":"ZLxPi+bfXrJ86aJuxiyYxJePkKzdtlqWtxNeslvm8fvf2QtSu+an9PaEx8wvzTDniMD/5/TVbh3rztr6AKS+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0e636d34e284efa3d0c2902d6d6e9d83e8b8b064845c771dcfa95134ae8965d","last_reissued_at":"2026-05-17T23:44:34.930961Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:34.930961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.13428","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":"2026-05-17T23:44:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8wF7tTLdiBAGGn2fHNpf8Cfik01SA5tYC0QTbSXCLplosPoKU9ZWEAMwiDkNJwKopRuFJ2iTGygO9iIAnKhGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:11:58.064021Z"},"content_sha256":"9905f5f576dcc446c3ebcb71969b39f12b148455457edcaec363ab034ee934d3","schema_version":"1.0","event_id":"sha256:9905f5f576dcc446c3ebcb71969b39f12b148455457edcaec363ab034ee934d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:6DTDNU2OFBHPUPIMFEBNNVXJ3A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attentional Policies for Cross-Context Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Matthew A. Wright, Roberto Horowitz","submitted_at":"2019-05-31T06:02:52Z","abstract_excerpt":"Many potential applications of reinforcement learning in the real world involve interacting with other agents whose numbers vary over time. We propose new neural policy architectures for these multi-agent problems. In contrast to other methods of training an individual, discrete policy for each agent and then enforcing cooperation through some additional inter-policy mechanism, we follow the spirit of recent work on the power of relational inductive biases in deep networks by learning multi-agent relationships at the policy level via an attentional architecture. In our method, all agents share"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13428","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":""},"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":"2026-05-17T23:44:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WPmgKtNUOt+/+WHPpVEjlONuDR6kf20H+qwLfO1K8YNGov6dB0FkVFIQU4MWevepD+pkhxdxQk6sssWkJCG8CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:11:58.064772Z"},"content_sha256":"788de4f45b86d80e578c0c0fbc9e0eba233fc8e248f02a0d331198d3e48c0c34","schema_version":"1.0","event_id":"sha256:788de4f45b86d80e578c0c0fbc9e0eba233fc8e248f02a0d331198d3e48c0c34"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6DTDNU2OFBHPUPIMFEBNNVXJ3A/bundle.json","state_url":"https://pith.science/pith/6DTDNU2OFBHPUPIMFEBNNVXJ3A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6DTDNU2OFBHPUPIMFEBNNVXJ3A/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":"2026-05-31T19:11:58Z","links":{"resolver":"https://pith.science/pith/6DTDNU2OFBHPUPIMFEBNNVXJ3A","bundle":"https://pith.science/pith/6DTDNU2OFBHPUPIMFEBNNVXJ3A/bundle.json","state":"https://pith.science/pith/6DTDNU2OFBHPUPIMFEBNNVXJ3A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6DTDNU2OFBHPUPIMFEBNNVXJ3A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:6DTDNU2OFBHPUPIMFEBNNVXJ3A","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":"61285761945103766d6a3e07ba643659bbddbdefed879b761a76d0dcf98bee7c","cross_cats_sorted":["cs.MA","cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T06:02:52Z","title_canon_sha256":"3b9ca0edfe7e6739ba1938c00456be91ea15c3567f8e02089eb4dded8c376cc5"},"schema_version":"1.0","source":{"id":"1905.13428","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.13428","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"arxiv_version","alias_value":"1905.13428v1","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13428","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"pith_short_12","alias_value":"6DTDNU2OFBHP","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6DTDNU2OFBHPUPIM","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6DTDNU2O","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:788de4f45b86d80e578c0c0fbc9e0eba233fc8e248f02a0d331198d3e48c0c34","target":"graph","created_at":"2026-05-17T23:44:34Z","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"},"paper":{"abstract_excerpt":"Many potential applications of reinforcement learning in the real world involve interacting with other agents whose numbers vary over time. We propose new neural policy architectures for these multi-agent problems. In contrast to other methods of training an individual, discrete policy for each agent and then enforcing cooperation through some additional inter-policy mechanism, we follow the spirit of recent work on the power of relational inductive biases in deep networks by learning multi-agent relationships at the policy level via an attentional architecture. In our method, all agents share","authors_text":"Matthew A. Wright, Roberto Horowitz","cross_cats":["cs.MA","cs.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T06:02:52Z","title":"Attentional Policies for Cross-Context Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13428","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":"sha256:9905f5f576dcc446c3ebcb71969b39f12b148455457edcaec363ab034ee934d3","target":"record","created_at":"2026-05-17T23:44:34Z","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":"61285761945103766d6a3e07ba643659bbddbdefed879b761a76d0dcf98bee7c","cross_cats_sorted":["cs.MA","cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T06:02:52Z","title_canon_sha256":"3b9ca0edfe7e6739ba1938c00456be91ea15c3567f8e02089eb4dded8c376cc5"},"schema_version":"1.0","source":{"id":"1905.13428","kind":"arxiv","version":1}},"canonical_sha256":"f0e636d34e284efa3d0c2902d6d6e9d83e8b8b064845c771dcfa95134ae8965d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0e636d34e284efa3d0c2902d6d6e9d83e8b8b064845c771dcfa95134ae8965d","first_computed_at":"2026-05-17T23:44:34.930961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:34.930961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZLxPi+bfXrJ86aJuxiyYxJePkKzdtlqWtxNeslvm8fvf2QtSu+an9PaEx8wvzTDniMD/5/TVbh3rztr6AKS+AQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:34.931449Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.13428","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9905f5f576dcc446c3ebcb71969b39f12b148455457edcaec363ab034ee934d3","sha256:788de4f45b86d80e578c0c0fbc9e0eba233fc8e248f02a0d331198d3e48c0c34"],"state_sha256":"60ab73cc661513792ebe92378dfd9a142f1194240a6ede9ad61ff392b1768d4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WJQHuLBxBf+MaZXrhb9Fld2BFGd+sIpidG2JcGLftmzcGO3xx5JDryOxTNewjf88gphDx4UWUq3E3cEK3NThAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T19:11:58.069234Z","bundle_sha256":"086d625f38b180c3b04ed5295380f81ae3344e22757504d0d0677766dc27e773"}}