{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3QWAVHKS4AP236O7FM3GFW7OF4","short_pith_number":"pith:3QWAVHKS","canonical_record":{"source":{"id":"2101.08001","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-20T07:24:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5cd3dd0497863021dfef8dc3be5e96be9a3432c6c3d6d24dab1c636a395b46f6","abstract_canon_sha256":"883781cf9ea4d264bdad755a3e7ad9694ed27add3f045749045cfa6acdd68a38"},"schema_version":"1.0"},"canonical_sha256":"dc2c0a9d52e01fadf9df2b3662dbee2f3be450028463c9db5172156ac985cd18","source":{"kind":"arxiv","id":"2101.08001","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.08001","created_at":"2026-07-05T02:13:21Z"},{"alias_kind":"arxiv_version","alias_value":"2101.08001v3","created_at":"2026-07-05T02:13:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.08001","created_at":"2026-07-05T02:13:21Z"},{"alias_kind":"pith_short_12","alias_value":"3QWAVHKS4AP2","created_at":"2026-07-05T02:13:21Z"},{"alias_kind":"pith_short_16","alias_value":"3QWAVHKS4AP236O7","created_at":"2026-07-05T02:13:21Z"},{"alias_kind":"pith_short_8","alias_value":"3QWAVHKS","created_at":"2026-07-05T02:13:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3QWAVHKS4AP236O7FM3GFW7OF4","target":"record","payload":{"canonical_record":{"source":{"id":"2101.08001","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-20T07:24:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5cd3dd0497863021dfef8dc3be5e96be9a3432c6c3d6d24dab1c636a395b46f6","abstract_canon_sha256":"883781cf9ea4d264bdad755a3e7ad9694ed27add3f045749045cfa6acdd68a38"},"schema_version":"1.0"},"canonical_sha256":"dc2c0a9d52e01fadf9df2b3662dbee2f3be450028463c9db5172156ac985cd18","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:21.830194Z","signature_b64":"W4QIC65glnCx2tvS8ElVc2dSIRTCswALYYHI0FLZwuU7ENMti5mEy+MZVTV+uCsfOLZTSPZ9Voy6KTsLblKpBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc2c0a9d52e01fadf9df2b3662dbee2f3be450028463c9db5172156ac985cd18","last_reissued_at":"2026-07-05T02:13:21.829792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:21.829792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.08001","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":"2026-07-05T02:13:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zWfPq+qeZ4BpvwmhQiLFhc4tADVyVUEhu0Bcx271y1LtVgi84N9uoRXXOh0VPicRLr5ZK4DSiBCsno8wFLYLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T10:46:45.135166Z"},"content_sha256":"2b9a920ed4cf16b4d7e00f511b559881f90abe025aee8085abbe8c609883bb11","schema_version":"1.0","event_id":"sha256:2b9a920ed4cf16b4d7e00f511b559881f90abe025aee8085abbe8c609883bb11"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3QWAVHKS4AP236O7FM3GFW7OF4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fengda Zhu, Siyi Hu, Xiaodan Liang, Xiaojun Chang","submitted_at":"2021-01-20T07:24:24Z","abstract_excerpt":"Recent advances in multi-agent reinforcement learning have been largely limited in training one model from scratch for every new task. The limitation is due to the restricted model architecture related to fixed input and output dimensions. This hinders the experience accumulation and transfer of the learned agent over tasks with diverse levels of difficulty (e.g. 3 vs 3 or 5 vs 6 multi-agent games). In this paper, we make the first attempt to explore a universal multi-agent reinforcement learning pipeline, designing one single architecture to fit tasks with the requirement of different observa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.08001","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/2101.08001/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":"2026-07-05T02:13:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PqhXrQqc7DCr+3AS3GN9UKyGxKjADatN5p3pnod5JEQuWmWq6nOUZ/POiBu6vn4gCe0z/j8aw96K6UTa/XWDDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T10:46:45.135557Z"},"content_sha256":"0e1372b66011c6e7c8632651a012664e4aab06d623875aef96966d7850f33022","schema_version":"1.0","event_id":"sha256:0e1372b66011c6e7c8632651a012664e4aab06d623875aef96966d7850f33022"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3QWAVHKS4AP236O7FM3GFW7OF4/bundle.json","state_url":"https://pith.science/pith/3QWAVHKS4AP236O7FM3GFW7OF4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3QWAVHKS4AP236O7FM3GFW7OF4/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":"2026-07-09T10:46:45Z","links":{"resolver":"https://pith.science/pith/3QWAVHKS4AP236O7FM3GFW7OF4","bundle":"https://pith.science/pith/3QWAVHKS4AP236O7FM3GFW7OF4/bundle.json","state":"https://pith.science/pith/3QWAVHKS4AP236O7FM3GFW7OF4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3QWAVHKS4AP236O7FM3GFW7OF4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3QWAVHKS4AP236O7FM3GFW7OF4","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":"883781cf9ea4d264bdad755a3e7ad9694ed27add3f045749045cfa6acdd68a38","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-20T07:24:24Z","title_canon_sha256":"5cd3dd0497863021dfef8dc3be5e96be9a3432c6c3d6d24dab1c636a395b46f6"},"schema_version":"1.0","source":{"id":"2101.08001","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.08001","created_at":"2026-07-05T02:13:21Z"},{"alias_kind":"arxiv_version","alias_value":"2101.08001v3","created_at":"2026-07-05T02:13:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.08001","created_at":"2026-07-05T02:13:21Z"},{"alias_kind":"pith_short_12","alias_value":"3QWAVHKS4AP2","created_at":"2026-07-05T02:13:21Z"},{"alias_kind":"pith_short_16","alias_value":"3QWAVHKS4AP236O7","created_at":"2026-07-05T02:13:21Z"},{"alias_kind":"pith_short_8","alias_value":"3QWAVHKS","created_at":"2026-07-05T02:13:21Z"}],"graph_snapshots":[{"event_id":"sha256:0e1372b66011c6e7c8632651a012664e4aab06d623875aef96966d7850f33022","target":"graph","created_at":"2026-07-05T02:13:21Z","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/2101.08001/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in multi-agent reinforcement learning have been largely limited in training one model from scratch for every new task. The limitation is due to the restricted model architecture related to fixed input and output dimensions. This hinders the experience accumulation and transfer of the learned agent over tasks with diverse levels of difficulty (e.g. 3 vs 3 or 5 vs 6 multi-agent games). In this paper, we make the first attempt to explore a universal multi-agent reinforcement learning pipeline, designing one single architecture to fit tasks with the requirement of different observa","authors_text":"Fengda Zhu, Siyi Hu, Xiaodan Liang, Xiaojun Chang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-20T07:24:24Z","title":"UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.08001","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":"sha256:2b9a920ed4cf16b4d7e00f511b559881f90abe025aee8085abbe8c609883bb11","target":"record","created_at":"2026-07-05T02:13:21Z","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":"883781cf9ea4d264bdad755a3e7ad9694ed27add3f045749045cfa6acdd68a38","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-20T07:24:24Z","title_canon_sha256":"5cd3dd0497863021dfef8dc3be5e96be9a3432c6c3d6d24dab1c636a395b46f6"},"schema_version":"1.0","source":{"id":"2101.08001","kind":"arxiv","version":3}},"canonical_sha256":"dc2c0a9d52e01fadf9df2b3662dbee2f3be450028463c9db5172156ac985cd18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc2c0a9d52e01fadf9df2b3662dbee2f3be450028463c9db5172156ac985cd18","first_computed_at":"2026-07-05T02:13:21.829792Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:13:21.829792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W4QIC65glnCx2tvS8ElVc2dSIRTCswALYYHI0FLZwuU7ENMti5mEy+MZVTV+uCsfOLZTSPZ9Voy6KTsLblKpBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:13:21.830194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.08001","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b9a920ed4cf16b4d7e00f511b559881f90abe025aee8085abbe8c609883bb11","sha256:0e1372b66011c6e7c8632651a012664e4aab06d623875aef96966d7850f33022"],"state_sha256":"dffe4c1f37d7a7c0edaae5585e3dd59d0196b2c11a69da84458a2bbff485af71"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mCHwBb01cTk9RrQ3tESrw+mM5KhoU6iLFVYaryctcTb715qa1TWuGLA6X3f6dIsCZxN68CchMJ0sTXYGZFpMAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T10:46:45.137556Z","bundle_sha256":"02f785b6768098abdb9bd2f3992243f3034e8558c5782aa0d83d63f0a2f0bba5"}}