{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:OYDVAEKRG627WSFXDRUQRNDEBJ","short_pith_number":"pith:OYDVAEKR","canonical_record":{"source":{"id":"1703.06182","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-17T19:32:38Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"e63964c3ee0b8048a0851a39365f7e1b88f03a9393ccd86152217e150242f5b5","abstract_canon_sha256":"e0416ca83c6c21aefdaf8bfe291e9397197640329773b7324715fa2b5a582f4f"},"schema_version":"1.0"},"canonical_sha256":"760750115137b5fb48b71c6908b4640a4bccd2033042ac2c6143a1390c05276d","source":{"kind":"arxiv","id":"1703.06182","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.06182","created_at":"2026-05-18T00:15:30Z"},{"alias_kind":"arxiv_version","alias_value":"1703.06182v4","created_at":"2026-05-18T00:15:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06182","created_at":"2026-05-18T00:15:30Z"},{"alias_kind":"pith_short_12","alias_value":"OYDVAEKRG627","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OYDVAEKRG627WSFX","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OYDVAEKR","created_at":"2026-05-18T12:31:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:OYDVAEKRG627WSFXDRUQRNDEBJ","target":"record","payload":{"canonical_record":{"source":{"id":"1703.06182","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-17T19:32:38Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"e63964c3ee0b8048a0851a39365f7e1b88f03a9393ccd86152217e150242f5b5","abstract_canon_sha256":"e0416ca83c6c21aefdaf8bfe291e9397197640329773b7324715fa2b5a582f4f"},"schema_version":"1.0"},"canonical_sha256":"760750115137b5fb48b71c6908b4640a4bccd2033042ac2c6143a1390c05276d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:30.842907Z","signature_b64":"EvjvAbmirUyg5XGax4jR2O9HfifnkzLVuZankXOP/anZ3S9Vm1ZFg7HJJDT21WuRLC83DSTXxuB9mSbBnxCeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"760750115137b5fb48b71c6908b4640a4bccd2033042ac2c6143a1390c05276d","last_reissued_at":"2026-05-18T00:15:30.842398Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:30.842398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.06182","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zYFfMmZaN5QvoiSxqH2jTqUTF2sFEPndw6oWkrBXmzL8XnV0frF3yQwHXQYbN3uGTJovCWIvM+rIWAcSOQAeCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T18:29:38.171896Z"},"content_sha256":"b63c87ba014d87d7dcec2886680750741d176caefb9565573bf0874d45d3c3ac","schema_version":"1.0","event_id":"sha256:b63c87ba014d87d7dcec2886680750741d176caefb9565573bf0874d45d3c3ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:OYDVAEKRG627WSFXDRUQRNDEBJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Christopher Amato, Jason Pazis, John Vian, Jonathan P. How, Shayegan Omidshafiei","submitted_at":"2017-03-17T19:32:38Z","abstract_excerpt":"Many real-world tasks involve multiple agents with partial observability and limited communication. Learning is challenging in these settings due to local viewpoints of agents, which perceive the world as non-stationary due to concurrently-exploring teammates. Approaches that learn specialized policies for individual tasks face problems when applied to the real world: not only do agents have to learn and store distinct policies for each task, but in practice identities of tasks are often non-observable, making these approaches inapplicable. This paper formalizes and addresses the problem of mu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06182","kind":"arxiv","version":4},"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":"2026-05-18T00:15:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sAuq630GLnbSvhMEZZX+wTqFU/hXfeaFYi4aqVOEQvQFrPTjwGSRGTDZkrdQ6jrYf79JWnOyFytSCSoEzsoRDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T18:29:38.172563Z"},"content_sha256":"da5bca45f87a1517ff62dcc783cce4646b0be028ac3881f37e4e1a0268d479da","schema_version":"1.0","event_id":"sha256:da5bca45f87a1517ff62dcc783cce4646b0be028ac3881f37e4e1a0268d479da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OYDVAEKRG627WSFXDRUQRNDEBJ/bundle.json","state_url":"https://pith.science/pith/OYDVAEKRG627WSFXDRUQRNDEBJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OYDVAEKRG627WSFXDRUQRNDEBJ/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":"2026-05-28T18:29:38Z","links":{"resolver":"https://pith.science/pith/OYDVAEKRG627WSFXDRUQRNDEBJ","bundle":"https://pith.science/pith/OYDVAEKRG627WSFXDRUQRNDEBJ/bundle.json","state":"https://pith.science/pith/OYDVAEKRG627WSFXDRUQRNDEBJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OYDVAEKRG627WSFXDRUQRNDEBJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:OYDVAEKRG627WSFXDRUQRNDEBJ","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":"e0416ca83c6c21aefdaf8bfe291e9397197640329773b7324715fa2b5a582f4f","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-17T19:32:38Z","title_canon_sha256":"e63964c3ee0b8048a0851a39365f7e1b88f03a9393ccd86152217e150242f5b5"},"schema_version":"1.0","source":{"id":"1703.06182","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.06182","created_at":"2026-05-18T00:15:30Z"},{"alias_kind":"arxiv_version","alias_value":"1703.06182v4","created_at":"2026-05-18T00:15:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06182","created_at":"2026-05-18T00:15:30Z"},{"alias_kind":"pith_short_12","alias_value":"OYDVAEKRG627","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OYDVAEKRG627WSFX","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OYDVAEKR","created_at":"2026-05-18T12:31:34Z"}],"graph_snapshots":[{"event_id":"sha256:da5bca45f87a1517ff62dcc783cce4646b0be028ac3881f37e4e1a0268d479da","target":"graph","created_at":"2026-05-18T00:15:30Z","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 real-world tasks involve multiple agents with partial observability and limited communication. Learning is challenging in these settings due to local viewpoints of agents, which perceive the world as non-stationary due to concurrently-exploring teammates. Approaches that learn specialized policies for individual tasks face problems when applied to the real world: not only do agents have to learn and store distinct policies for each task, but in practice identities of tasks are often non-observable, making these approaches inapplicable. This paper formalizes and addresses the problem of mu","authors_text":"Christopher Amato, Jason Pazis, John Vian, Jonathan P. How, Shayegan Omidshafiei","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-17T19:32:38Z","title":"Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06182","kind":"arxiv","version":4},"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:b63c87ba014d87d7dcec2886680750741d176caefb9565573bf0874d45d3c3ac","target":"record","created_at":"2026-05-18T00:15:30Z","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":"e0416ca83c6c21aefdaf8bfe291e9397197640329773b7324715fa2b5a582f4f","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-17T19:32:38Z","title_canon_sha256":"e63964c3ee0b8048a0851a39365f7e1b88f03a9393ccd86152217e150242f5b5"},"schema_version":"1.0","source":{"id":"1703.06182","kind":"arxiv","version":4}},"canonical_sha256":"760750115137b5fb48b71c6908b4640a4bccd2033042ac2c6143a1390c05276d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"760750115137b5fb48b71c6908b4640a4bccd2033042ac2c6143a1390c05276d","first_computed_at":"2026-05-18T00:15:30.842398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:30.842398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EvjvAbmirUyg5XGax4jR2O9HfifnkzLVuZankXOP/anZ3S9Vm1ZFg7HJJDT21WuRLC83DSTXxuB9mSbBnxCeAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:30.842907Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.06182","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b63c87ba014d87d7dcec2886680750741d176caefb9565573bf0874d45d3c3ac","sha256:da5bca45f87a1517ff62dcc783cce4646b0be028ac3881f37e4e1a0268d479da"],"state_sha256":"11d773e80d90ded78cca59640150e679c4a703a54c3f94e244de505c2a61df8d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8XoFfrX3gDffn4AMqBykD+69FEZFJWatlc91C81BHtJ2ul2JFCTpZ4gFwizc/sBKui/CP3hMgIj8wga24B1xAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T18:29:38.176327Z","bundle_sha256":"7d63cd8a00b8468a12ecdabb3066e3ff8e73fb4ec028cf1289d1ecf8eeb239c7"}}