{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:2ZWCO7FH6BNCOWQF45UTQS27Q4","short_pith_number":"pith:2ZWCO7FH","canonical_record":{"source":{"id":"2007.01962","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-07-03T23:08:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"714e9f10fce3f3f84471b65259e0f893f929728cb3c08c9c76a5d75e7bd60501","abstract_canon_sha256":"3cdc098a223e3be12cefaebb7a9ead03e2762202e7bf6c70e8a9acd58262a546"},"schema_version":"1.0"},"canonical_sha256":"d66c277ca7f05a275a05e769384b5f870d7d8ec491d24b9a8546fa82b24e8f2c","source":{"kind":"arxiv","id":"2007.01962","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.01962","created_at":"2026-07-05T02:49:11Z"},{"alias_kind":"arxiv_version","alias_value":"2007.01962v2","created_at":"2026-07-05T02:49:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.01962","created_at":"2026-07-05T02:49:11Z"},{"alias_kind":"pith_short_12","alias_value":"2ZWCO7FH6BNC","created_at":"2026-07-05T02:49:11Z"},{"alias_kind":"pith_short_16","alias_value":"2ZWCO7FH6BNCOWQF","created_at":"2026-07-05T02:49:11Z"},{"alias_kind":"pith_short_8","alias_value":"2ZWCO7FH","created_at":"2026-07-05T02:49:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:2ZWCO7FH6BNCOWQF45UTQS27Q4","target":"record","payload":{"canonical_record":{"source":{"id":"2007.01962","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-07-03T23:08:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"714e9f10fce3f3f84471b65259e0f893f929728cb3c08c9c76a5d75e7bd60501","abstract_canon_sha256":"3cdc098a223e3be12cefaebb7a9ead03e2762202e7bf6c70e8a9acd58262a546"},"schema_version":"1.0"},"canonical_sha256":"d66c277ca7f05a275a05e769384b5f870d7d8ec491d24b9a8546fa82b24e8f2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:11.343773Z","signature_b64":"LxjHz4trdwSl72VylGp3vjjQBjIsRPsQALoYatG+2tLyaEME2/g7J3kkW9NI4mNL9vfcaAoBk5aTzA8wqg+eCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d66c277ca7f05a275a05e769384b5f870d7d8ec491d24b9a8546fa82b24e8f2c","last_reissued_at":"2026-07-05T02:49:11.343278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:11.343278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.01962","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:49:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zu7bYb2j4wvvPgLhqcPT/GhYL1wQIBrrXddLvC5isl1lI8U1klWFAE9ki4M2cllSCxKE92WKtC6O9NR89UWUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:53:12.527813Z"},"content_sha256":"27229f8b55867bc597ed7cb249cfbcf0042b484d76ddb6609cddc42ee956a974","schema_version":"1.0","event_id":"sha256:27229f8b55867bc597ed7cb249cfbcf0042b484d76ddb6609cddc42ee956a974"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:2ZWCO7FH6BNCOWQF45UTQS27Q4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reward Machines for Cooperative Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Bo Wu, Cyrus Neary, Ufuk Topcu, Zhe Xu","submitted_at":"2020-07-03T23:08:14Z","abstract_excerpt":"In cooperative multi-agent reinforcement learning, a collection of agents learns to interact in a shared environment to achieve a common goal. We propose the use of reward machines (RM) -- Mealy machines used as structured representations of reward functions -- to encode the team's task. The proposed novel interpretation of RMs in the multi-agent setting explicitly encodes required teammate interdependencies, allowing the team-level task to be decomposed into sub-tasks for individual agents. We define such a notion of RM decomposition and present algorithmically verifiable conditions guarantee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.01962","kind":"arxiv","version":2},"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/2007.01962/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":"2026-07-05T02:49:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PYi7Y/Hz5QftrnnaFypGhy0ks2EBSuN+IDY6elYXUCT4CslknZbK/dNYT2cBPYBA2auN0IYtDKyTXlMTqNPkAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:53:12.528311Z"},"content_sha256":"060c7c19852a406efb0d2c484fa5b63d3addeaa62f5584f08d3a326c7af3842b","schema_version":"1.0","event_id":"sha256:060c7c19852a406efb0d2c484fa5b63d3addeaa62f5584f08d3a326c7af3842b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2ZWCO7FH6BNCOWQF45UTQS27Q4/bundle.json","state_url":"https://pith.science/pith/2ZWCO7FH6BNCOWQF45UTQS27Q4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2ZWCO7FH6BNCOWQF45UTQS27Q4/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":"2026-08-10T16:53:12Z","links":{"resolver":"https://pith.science/pith/2ZWCO7FH6BNCOWQF45UTQS27Q4","bundle":"https://pith.science/pith/2ZWCO7FH6BNCOWQF45UTQS27Q4/bundle.json","state":"https://pith.science/pith/2ZWCO7FH6BNCOWQF45UTQS27Q4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2ZWCO7FH6BNCOWQF45UTQS27Q4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2ZWCO7FH6BNCOWQF45UTQS27Q4","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":"3cdc098a223e3be12cefaebb7a9ead03e2762202e7bf6c70e8a9acd58262a546","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-07-03T23:08:14Z","title_canon_sha256":"714e9f10fce3f3f84471b65259e0f893f929728cb3c08c9c76a5d75e7bd60501"},"schema_version":"1.0","source":{"id":"2007.01962","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.01962","created_at":"2026-07-05T02:49:11Z"},{"alias_kind":"arxiv_version","alias_value":"2007.01962v2","created_at":"2026-07-05T02:49:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.01962","created_at":"2026-07-05T02:49:11Z"},{"alias_kind":"pith_short_12","alias_value":"2ZWCO7FH6BNC","created_at":"2026-07-05T02:49:11Z"},{"alias_kind":"pith_short_16","alias_value":"2ZWCO7FH6BNCOWQF","created_at":"2026-07-05T02:49:11Z"},{"alias_kind":"pith_short_8","alias_value":"2ZWCO7FH","created_at":"2026-07-05T02:49:11Z"}],"graph_snapshots":[{"event_id":"sha256:060c7c19852a406efb0d2c484fa5b63d3addeaa62f5584f08d3a326c7af3842b","target":"graph","created_at":"2026-07-05T02:49:11Z","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/2007.01962/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In cooperative multi-agent reinforcement learning, a collection of agents learns to interact in a shared environment to achieve a common goal. We propose the use of reward machines (RM) -- Mealy machines used as structured representations of reward functions -- to encode the team's task. The proposed novel interpretation of RMs in the multi-agent setting explicitly encodes required teammate interdependencies, allowing the team-level task to be decomposed into sub-tasks for individual agents. We define such a notion of RM decomposition and present algorithmically verifiable conditions guarantee","authors_text":"Bo Wu, Cyrus Neary, Ufuk Topcu, Zhe Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-07-03T23:08:14Z","title":"Reward Machines for Cooperative Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.01962","kind":"arxiv","version":2},"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":"sha256:27229f8b55867bc597ed7cb249cfbcf0042b484d76ddb6609cddc42ee956a974","target":"record","created_at":"2026-07-05T02:49:11Z","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":"3cdc098a223e3be12cefaebb7a9ead03e2762202e7bf6c70e8a9acd58262a546","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-07-03T23:08:14Z","title_canon_sha256":"714e9f10fce3f3f84471b65259e0f893f929728cb3c08c9c76a5d75e7bd60501"},"schema_version":"1.0","source":{"id":"2007.01962","kind":"arxiv","version":2}},"canonical_sha256":"d66c277ca7f05a275a05e769384b5f870d7d8ec491d24b9a8546fa82b24e8f2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d66c277ca7f05a275a05e769384b5f870d7d8ec491d24b9a8546fa82b24e8f2c","first_computed_at":"2026-07-05T02:49:11.343278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:11.343278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LxjHz4trdwSl72VylGp3vjjQBjIsRPsQALoYatG+2tLyaEME2/g7J3kkW9NI4mNL9vfcaAoBk5aTzA8wqg+eCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:11.343773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.01962","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27229f8b55867bc597ed7cb249cfbcf0042b484d76ddb6609cddc42ee956a974","sha256:060c7c19852a406efb0d2c484fa5b63d3addeaa62f5584f08d3a326c7af3842b"],"state_sha256":"4231f820222877c3fd3a2e6b568f9344c3ff7b95a4246a5777d2595dd15ec885"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xlBPclHXOpp9G8n9vB9GC+j9yRlLVdqzS6kjcasVYnlQxc/MDgEettPyg2SoIbbrCoCHBc0KZvsDPbEp70LMAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T16:53:12.532339Z","bundle_sha256":"a14be2e8204d75ead41f6fd620c14a52fe89dd173d98a4ae6c9ca03e0a51c4fb"}}