{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZVDVGKYBYOE6M33N2A2Q2ISIXA","short_pith_number":"pith:ZVDVGKYB","canonical_record":{"source":{"id":"1810.00147","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-09-29T04:33:15Z","cross_cats_sorted":["cs.LG","cs.MA","stat.ML"],"title_canon_sha256":"1f76c5dc09a57f361a7adadaa012dd0d1432a90ec753055f70f8c92389b0087b","abstract_canon_sha256":"78e825731617b19975c7452b01823814cbf93eb9b1251f1c688d2d81299f59be"},"schema_version":"1.0"},"canonical_sha256":"cd47532b01c389e66f6dd0350d2248b811498bf9057f8de1ae1b6162c9814d82","source":{"kind":"arxiv","id":"1810.00147","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00147","created_at":"2026-05-17T23:51:52Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00147v3","created_at":"2026-05-17T23:51:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00147","created_at":"2026-05-17T23:51:52Z"},{"alias_kind":"pith_short_12","alias_value":"ZVDVGKYBYOE6","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZVDVGKYBYOE6M33N","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZVDVGKYB","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZVDVGKYBYOE6M33N2A2Q2ISIXA","target":"record","payload":{"canonical_record":{"source":{"id":"1810.00147","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-09-29T04:33:15Z","cross_cats_sorted":["cs.LG","cs.MA","stat.ML"],"title_canon_sha256":"1f76c5dc09a57f361a7adadaa012dd0d1432a90ec753055f70f8c92389b0087b","abstract_canon_sha256":"78e825731617b19975c7452b01823814cbf93eb9b1251f1c688d2d81299f59be"},"schema_version":"1.0"},"canonical_sha256":"cd47532b01c389e66f6dd0350d2248b811498bf9057f8de1ae1b6162c9814d82","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:52.500698Z","signature_b64":"8Q1yae/QVJyK9KTj/LENxDQ4+nuP7sbD+/axdNKDq6k0pwcN/FA25Rv3H0oXO2a8+ZNkUr9oEc8AYqG8MjUqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd47532b01c389e66f6dd0350d2248b811498bf9057f8de1ae1b6162c9814d82","last_reissued_at":"2026-05-17T23:51:52.499975Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:52.499975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.00147","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":"2026-05-17T23:51:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3v2KqRbuRUJBLSSUPSIuLy4aGuoMquzOHmF1C71cuGk6kKYvsklC/QrbyH7yDp8ucK3uijPRz0SpNxO4GDmsDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T09:12:41.065703Z"},"content_sha256":"e220994d71d371e5dbf61f8b62507dab9c159d6455f787d161baedb3c094eba4","schema_version":"1.0","event_id":"sha256:e220994d71d371e5dbf61f8b62507dab9c159d6455f787d161baedb3c094eba4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZVDVGKYBYOE6M33N2A2Q2ISIXA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"M$^3$RL: Mind-aware Multi-agent Management Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA","stat.ML"],"primary_cat":"cs.AI","authors_text":"Tianmin Shu, Yuandong Tian","submitted_at":"2018-09-29T04:33:15Z","abstract_excerpt":"Most of the prior work on multi-agent reinforcement learning (MARL) achieves optimal collaboration by directly controlling the agents to maximize a common reward. In this paper, we aim to address this from a different angle. In particular, we consider scenarios where there are self-interested agents (i.e., worker agents) which have their own minds (preferences, intentions, skills, etc.) and can not be dictated to perform tasks they do not wish to do. For achieving optimal coordination among these agents, we train a super agent (i.e., the manager) to manage them by first inferring their minds b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00147","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":""},"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":"2026-05-17T23:51:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xJJK8cFtfWave601gXey5k6mqmeRJ7LZM3p7IFg/nLeVNLHrC8vdZsHBiKH/Nm/PmXwe4JXcgB3m0I7a2LH6AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T09:12:41.066046Z"},"content_sha256":"6294e07447d75fc038cb3bc39b9507cdeeb4190c3ae79acc7f9c3d3c6c678b26","schema_version":"1.0","event_id":"sha256:6294e07447d75fc038cb3bc39b9507cdeeb4190c3ae79acc7f9c3d3c6c678b26"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZVDVGKYBYOE6M33N2A2Q2ISIXA/bundle.json","state_url":"https://pith.science/pith/ZVDVGKYBYOE6M33N2A2Q2ISIXA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZVDVGKYBYOE6M33N2A2Q2ISIXA/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":"2026-06-03T09:12:41Z","links":{"resolver":"https://pith.science/pith/ZVDVGKYBYOE6M33N2A2Q2ISIXA","bundle":"https://pith.science/pith/ZVDVGKYBYOE6M33N2A2Q2ISIXA/bundle.json","state":"https://pith.science/pith/ZVDVGKYBYOE6M33N2A2Q2ISIXA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZVDVGKYBYOE6M33N2A2Q2ISIXA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZVDVGKYBYOE6M33N2A2Q2ISIXA","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":"78e825731617b19975c7452b01823814cbf93eb9b1251f1c688d2d81299f59be","cross_cats_sorted":["cs.LG","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-09-29T04:33:15Z","title_canon_sha256":"1f76c5dc09a57f361a7adadaa012dd0d1432a90ec753055f70f8c92389b0087b"},"schema_version":"1.0","source":{"id":"1810.00147","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00147","created_at":"2026-05-17T23:51:52Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00147v3","created_at":"2026-05-17T23:51:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00147","created_at":"2026-05-17T23:51:52Z"},{"alias_kind":"pith_short_12","alias_value":"ZVDVGKYBYOE6","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZVDVGKYBYOE6M33N","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZVDVGKYB","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:6294e07447d75fc038cb3bc39b9507cdeeb4190c3ae79acc7f9c3d3c6c678b26","target":"graph","created_at":"2026-05-17T23:51:52Z","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":"Most of the prior work on multi-agent reinforcement learning (MARL) achieves optimal collaboration by directly controlling the agents to maximize a common reward. In this paper, we aim to address this from a different angle. In particular, we consider scenarios where there are self-interested agents (i.e., worker agents) which have their own minds (preferences, intentions, skills, etc.) and can not be dictated to perform tasks they do not wish to do. For achieving optimal coordination among these agents, we train a super agent (i.e., the manager) to manage them by first inferring their minds b","authors_text":"Tianmin Shu, Yuandong Tian","cross_cats":["cs.LG","cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-09-29T04:33:15Z","title":"M$^3$RL: Mind-aware Multi-agent Management Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00147","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:e220994d71d371e5dbf61f8b62507dab9c159d6455f787d161baedb3c094eba4","target":"record","created_at":"2026-05-17T23:51:52Z","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":"78e825731617b19975c7452b01823814cbf93eb9b1251f1c688d2d81299f59be","cross_cats_sorted":["cs.LG","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-09-29T04:33:15Z","title_canon_sha256":"1f76c5dc09a57f361a7adadaa012dd0d1432a90ec753055f70f8c92389b0087b"},"schema_version":"1.0","source":{"id":"1810.00147","kind":"arxiv","version":3}},"canonical_sha256":"cd47532b01c389e66f6dd0350d2248b811498bf9057f8de1ae1b6162c9814d82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd47532b01c389e66f6dd0350d2248b811498bf9057f8de1ae1b6162c9814d82","first_computed_at":"2026-05-17T23:51:52.499975Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:52.499975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Q1yae/QVJyK9KTj/LENxDQ4+nuP7sbD+/axdNKDq6k0pwcN/FA25Rv3H0oXO2a8+ZNkUr9oEc8AYqG8MjUqCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:52.500698Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.00147","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e220994d71d371e5dbf61f8b62507dab9c159d6455f787d161baedb3c094eba4","sha256:6294e07447d75fc038cb3bc39b9507cdeeb4190c3ae79acc7f9c3d3c6c678b26"],"state_sha256":"613b2ce5d68231be3ef2fc444aa4e7f96800fee7d0da1efdcafeff9f2b538e28"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"035wgKPBFgeJMIL1muj4id4aGDwI5HSqX2ArH97eQnCIFpG/ViS3WFkzo/khAHOe6T0OssupLy8KZRsX05zPBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T09:12:41.067977Z","bundle_sha256":"c1056a2d6b49a4210684a7b46611b4856e1d147e5e6d9a8c53e6eb80de841ad2"}}