{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AGBLG2CIIOWMTNIGIUFJV5D6E6","short_pith_number":"pith:AGBLG2CI","canonical_record":{"source":{"id":"2302.04944","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2023-02-09T21:24:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b51aef2e98d497e6974ef0280660488cf34000ed1959967698fff004fb13ce3f","abstract_canon_sha256":"114baa37a88c6313fa42bf8d9e24177e1f395819b094d45b485bc7c205f63d41"},"schema_version":"1.0"},"canonical_sha256":"0182b3684843acc9b506450a9af47e27a5d3b959c1bffc38ac4739e9abd45c41","source":{"kind":"arxiv","id":"2302.04944","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.04944","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"arxiv_version","alias_value":"2302.04944v2","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04944","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"pith_short_12","alias_value":"AGBLG2CIIOWM","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"pith_short_16","alias_value":"AGBLG2CIIOWMTNIG","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"pith_short_8","alias_value":"AGBLG2CI","created_at":"2026-07-05T07:45:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AGBLG2CIIOWMTNIGIUFJV5D6E6","target":"record","payload":{"canonical_record":{"source":{"id":"2302.04944","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2023-02-09T21:24:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b51aef2e98d497e6974ef0280660488cf34000ed1959967698fff004fb13ce3f","abstract_canon_sha256":"114baa37a88c6313fa42bf8d9e24177e1f395819b094d45b485bc7c205f63d41"},"schema_version":"1.0"},"canonical_sha256":"0182b3684843acc9b506450a9af47e27a5d3b959c1bffc38ac4739e9abd45c41","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:26.183074Z","signature_b64":"yc0mHg95tOXKLYlCzS1PGG9WiMkKZe7vAwbLPHgLYpK5Hx4t4Qy7ThHM8Bh5o+xOczs+81xpyUdfmd+GRZw6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0182b3684843acc9b506450a9af47e27a5d3b959c1bffc38ac4739e9abd45c41","last_reissued_at":"2026-07-05T07:45:26.182576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:26.182576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.04944","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":"2026-07-05T07:45:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y9E3Sir47lGlseoqSHQuMfdLibKh7TYMSCuITCiyDshVPEmVvB6hkNjyeSD0wF6PEJr6WymOzovEpWsJq4oDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:35:59.612544Z"},"content_sha256":"7f1c6396816eeec6eade67b671353dd2e364fd46065f8eaa21443d174bf2aa63","schema_version":"1.0","event_id":"sha256:7f1c6396816eeec6eade67b671353dd2e364fd46065f8eaa21443d174bf2aa63"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AGBLG2CIIOWMTNIGIUFJV5D6E6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Complex Teamwork Tasks Using a Given Sub-task Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Arrasy Rahman, Elliot Fosong, Ignacio Carlucho, Stefano V. Albrecht","submitted_at":"2023-02-09T21:24:56Z","abstract_excerpt":"Training a team to complete a complex task via multi-agent reinforcement learning can be difficult due to challenges such as policy search in a large joint policy space, and non-stationarity caused by mutually adapting agents. To facilitate efficient learning of complex multi-agent tasks, we propose an approach which uses an expert-provided decomposition of a task into simpler multi-agent sub-tasks. In each sub-task, a subset of the entire team is trained to acquire sub-task-specific policies. The sub-teams are then merged and transferred to the target task, where their policies are collective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04944","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/2302.04944/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":"2026-07-05T07:45:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AMswSsOw3KXoJhWGx216bx7bJrJ9ANwnAMj+UuflZATH4paMB2EaRDFNMV0YjVoLkEWarv0gkIdAWyN8W1xIBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:35:59.613159Z"},"content_sha256":"9978b87746d0b3af1d85b5800d99235a8d40b84ed00ff16ca087e7dc388e1cd7","schema_version":"1.0","event_id":"sha256:9978b87746d0b3af1d85b5800d99235a8d40b84ed00ff16ca087e7dc388e1cd7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AGBLG2CIIOWMTNIGIUFJV5D6E6/bundle.json","state_url":"https://pith.science/pith/AGBLG2CIIOWMTNIGIUFJV5D6E6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AGBLG2CIIOWMTNIGIUFJV5D6E6/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":"2026-08-18T18:35:59Z","links":{"resolver":"https://pith.science/pith/AGBLG2CIIOWMTNIGIUFJV5D6E6","bundle":"https://pith.science/pith/AGBLG2CIIOWMTNIGIUFJV5D6E6/bundle.json","state":"https://pith.science/pith/AGBLG2CIIOWMTNIGIUFJV5D6E6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AGBLG2CIIOWMTNIGIUFJV5D6E6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AGBLG2CIIOWMTNIGIUFJV5D6E6","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":"114baa37a88c6313fa42bf8d9e24177e1f395819b094d45b485bc7c205f63d41","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2023-02-09T21:24:56Z","title_canon_sha256":"b51aef2e98d497e6974ef0280660488cf34000ed1959967698fff004fb13ce3f"},"schema_version":"1.0","source":{"id":"2302.04944","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.04944","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"arxiv_version","alias_value":"2302.04944v2","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04944","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"pith_short_12","alias_value":"AGBLG2CIIOWM","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"pith_short_16","alias_value":"AGBLG2CIIOWMTNIG","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"pith_short_8","alias_value":"AGBLG2CI","created_at":"2026-07-05T07:45:26Z"}],"graph_snapshots":[{"event_id":"sha256:9978b87746d0b3af1d85b5800d99235a8d40b84ed00ff16ca087e7dc388e1cd7","target":"graph","created_at":"2026-07-05T07:45:26Z","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/2302.04944/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training a team to complete a complex task via multi-agent reinforcement learning can be difficult due to challenges such as policy search in a large joint policy space, and non-stationarity caused by mutually adapting agents. To facilitate efficient learning of complex multi-agent tasks, we propose an approach which uses an expert-provided decomposition of a task into simpler multi-agent sub-tasks. In each sub-task, a subset of the entire team is trained to acquire sub-task-specific policies. The sub-teams are then merged and transferred to the target task, where their policies are collective","authors_text":"Arrasy Rahman, Elliot Fosong, Ignacio Carlucho, Stefano V. Albrecht","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2023-02-09T21:24:56Z","title":"Learning Complex Teamwork Tasks Using a Given Sub-task Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04944","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":"sha256:7f1c6396816eeec6eade67b671353dd2e364fd46065f8eaa21443d174bf2aa63","target":"record","created_at":"2026-07-05T07:45:26Z","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":"114baa37a88c6313fa42bf8d9e24177e1f395819b094d45b485bc7c205f63d41","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2023-02-09T21:24:56Z","title_canon_sha256":"b51aef2e98d497e6974ef0280660488cf34000ed1959967698fff004fb13ce3f"},"schema_version":"1.0","source":{"id":"2302.04944","kind":"arxiv","version":2}},"canonical_sha256":"0182b3684843acc9b506450a9af47e27a5d3b959c1bffc38ac4739e9abd45c41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0182b3684843acc9b506450a9af47e27a5d3b959c1bffc38ac4739e9abd45c41","first_computed_at":"2026-07-05T07:45:26.182576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:45:26.182576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yc0mHg95tOXKLYlCzS1PGG9WiMkKZe7vAwbLPHgLYpK5Hx4t4Qy7ThHM8Bh5o+xOczs+81xpyUdfmd+GRZw6CA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:45:26.183074Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.04944","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f1c6396816eeec6eade67b671353dd2e364fd46065f8eaa21443d174bf2aa63","sha256:9978b87746d0b3af1d85b5800d99235a8d40b84ed00ff16ca087e7dc388e1cd7"],"state_sha256":"36203cc77f73b7a3fabbb0ab50bd2d564687d0647704b012a954af6c76f03df6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MRKp0b7VHegck9CMVqEyBrlwNff+WjahCDXj7XyW0sJdsg+/inMoeqvn4i/+4Xs9fYNnNwCDi30+L+dx/JHECw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T18:35:59.617220Z","bundle_sha256":"86b78583844995e4a5088c9d5aea5ed8a4f5ab1145394ac7aa39b0a3fa8e92b3"}}