{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WB6D3BYFHUOLX3UJUDY4T34HOR","short_pith_number":"pith:WB6D3BYF","canonical_record":{"source":{"id":"2404.10740","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-04-16T17:13:08Z","cross_cats_sorted":[],"title_canon_sha256":"6b4cd89ff7112f96b409d0d79c53abe98c2100358b8043fd36d4ff23b621dcb1","abstract_canon_sha256":"e052d3c589670c38227c1249fa67c2aed131404de627b6fb3782079a91cdccef"},"schema_version":"1.0"},"canonical_sha256":"b07c3d87053d1cbbee89a0f1c9ef87746cb348257ccef7b75fcda2c294cb0e61","source":{"kind":"arxiv","id":"2404.10740","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10740","created_at":"2026-07-05T11:54:39Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10740v3","created_at":"2026-07-05T11:54:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10740","created_at":"2026-07-05T11:54:39Z"},{"alias_kind":"pith_short_12","alias_value":"WB6D3BYFHUOL","created_at":"2026-07-05T11:54:39Z"},{"alias_kind":"pith_short_16","alias_value":"WB6D3BYFHUOLX3UJ","created_at":"2026-07-05T11:54:39Z"},{"alias_kind":"pith_short_8","alias_value":"WB6D3BYF","created_at":"2026-07-05T11:54:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WB6D3BYFHUOLX3UJUDY4T34HOR","target":"record","payload":{"canonical_record":{"source":{"id":"2404.10740","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-04-16T17:13:08Z","cross_cats_sorted":[],"title_canon_sha256":"6b4cd89ff7112f96b409d0d79c53abe98c2100358b8043fd36d4ff23b621dcb1","abstract_canon_sha256":"e052d3c589670c38227c1249fa67c2aed131404de627b6fb3782079a91cdccef"},"schema_version":"1.0"},"canonical_sha256":"b07c3d87053d1cbbee89a0f1c9ef87746cb348257ccef7b75fcda2c294cb0e61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:39.491928Z","signature_b64":"WDPz8VeT0ZViaO970wAKvgoVJzUPSifBR0SW7xh0AgassKw1hUfG1hKhI+HVvd4bCauFSCYDGPr0dyhko4QmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b07c3d87053d1cbbee89a0f1c9ef87746cb348257ccef7b75fcda2c294cb0e61","last_reissued_at":"2026-07-05T11:54:39.491399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:39.491399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.10740","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":"2026-07-05T11:54:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5u0wl3/pgfkXkZJYTMLVAb//yjWpXQ8M05uxS92CU3RCsq+nA5gxG0zv9XC4oXcoj863T+/uftfduNXFppaDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:06:25.486540Z"},"content_sha256":"7c97a14f53dbd79aebb49bf33994f7ec37ebecdf9199e0dfed22385fcd090495","schema_version":"1.0","event_id":"sha256:7c97a14f53dbd79aebb49bf33994f7ec37ebecdf9199e0dfed22385fcd090495"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WB6D3BYFHUOLX3UJUDY4T34HOR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"N-Agent Ad Hoc Teamwork","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Arrasy Rahman, Caroline Wang, Elad Liebman, Ishan Durugkar, Peter Stone","submitted_at":"2024-04-16T17:13:08Z","abstract_excerpt":"Current approaches to learning cooperative multi-agent behaviors assume relatively restrictive settings. In standard fully cooperative multi-agent reinforcement learning, the learning algorithm controls $\\textit{all}$ agents in the scenario, while in ad hoc teamwork, the learning algorithm usually assumes control over only a $\\textit{single}$ agent in the scenario. However, many cooperative settings in the real world are much less restrictive. For example, in an autonomous driving scenario, a company might train its cars with the same learning algorithm, yet once on the road, these cars must c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10740","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/2404.10740/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":"2026-07-05T11:54:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Aoj6875bfAc2tMWhad6ko2mu9vpW2Wcf/Wx9c+QrYdYYeJcLOCtJPPwLvXZPzw0ruIZGMYLGtTnR8tMbwn/QAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:06:25.487060Z"},"content_sha256":"5c9b419d99640a0d10484caeca4f2574c73d8da49d57986d84785afd1bc59b69","schema_version":"1.0","event_id":"sha256:5c9b419d99640a0d10484caeca4f2574c73d8da49d57986d84785afd1bc59b69"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WB6D3BYFHUOLX3UJUDY4T34HOR/bundle.json","state_url":"https://pith.science/pith/WB6D3BYFHUOLX3UJUDY4T34HOR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WB6D3BYFHUOLX3UJUDY4T34HOR/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":"2026-08-11T01:06:25Z","links":{"resolver":"https://pith.science/pith/WB6D3BYFHUOLX3UJUDY4T34HOR","bundle":"https://pith.science/pith/WB6D3BYFHUOLX3UJUDY4T34HOR/bundle.json","state":"https://pith.science/pith/WB6D3BYFHUOLX3UJUDY4T34HOR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WB6D3BYFHUOLX3UJUDY4T34HOR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WB6D3BYFHUOLX3UJUDY4T34HOR","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":"e052d3c589670c38227c1249fa67c2aed131404de627b6fb3782079a91cdccef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-04-16T17:13:08Z","title_canon_sha256":"6b4cd89ff7112f96b409d0d79c53abe98c2100358b8043fd36d4ff23b621dcb1"},"schema_version":"1.0","source":{"id":"2404.10740","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10740","created_at":"2026-07-05T11:54:39Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10740v3","created_at":"2026-07-05T11:54:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10740","created_at":"2026-07-05T11:54:39Z"},{"alias_kind":"pith_short_12","alias_value":"WB6D3BYFHUOL","created_at":"2026-07-05T11:54:39Z"},{"alias_kind":"pith_short_16","alias_value":"WB6D3BYFHUOLX3UJ","created_at":"2026-07-05T11:54:39Z"},{"alias_kind":"pith_short_8","alias_value":"WB6D3BYF","created_at":"2026-07-05T11:54:39Z"}],"graph_snapshots":[{"event_id":"sha256:5c9b419d99640a0d10484caeca4f2574c73d8da49d57986d84785afd1bc59b69","target":"graph","created_at":"2026-07-05T11:54:39Z","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/2404.10740/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current approaches to learning cooperative multi-agent behaviors assume relatively restrictive settings. In standard fully cooperative multi-agent reinforcement learning, the learning algorithm controls $\\textit{all}$ agents in the scenario, while in ad hoc teamwork, the learning algorithm usually assumes control over only a $\\textit{single}$ agent in the scenario. However, many cooperative settings in the real world are much less restrictive. For example, in an autonomous driving scenario, a company might train its cars with the same learning algorithm, yet once on the road, these cars must c","authors_text":"Arrasy Rahman, Caroline Wang, Elad Liebman, Ishan Durugkar, Peter Stone","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-04-16T17:13:08Z","title":"N-Agent Ad Hoc Teamwork"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10740","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":"sha256:7c97a14f53dbd79aebb49bf33994f7ec37ebecdf9199e0dfed22385fcd090495","target":"record","created_at":"2026-07-05T11:54:39Z","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":"e052d3c589670c38227c1249fa67c2aed131404de627b6fb3782079a91cdccef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-04-16T17:13:08Z","title_canon_sha256":"6b4cd89ff7112f96b409d0d79c53abe98c2100358b8043fd36d4ff23b621dcb1"},"schema_version":"1.0","source":{"id":"2404.10740","kind":"arxiv","version":3}},"canonical_sha256":"b07c3d87053d1cbbee89a0f1c9ef87746cb348257ccef7b75fcda2c294cb0e61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b07c3d87053d1cbbee89a0f1c9ef87746cb348257ccef7b75fcda2c294cb0e61","first_computed_at":"2026-07-05T11:54:39.491399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:39.491399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WDPz8VeT0ZViaO970wAKvgoVJzUPSifBR0SW7xh0AgassKw1hUfG1hKhI+HVvd4bCauFSCYDGPr0dyhko4QmBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:39.491928Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.10740","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c97a14f53dbd79aebb49bf33994f7ec37ebecdf9199e0dfed22385fcd090495","sha256:5c9b419d99640a0d10484caeca4f2574c73d8da49d57986d84785afd1bc59b69"],"state_sha256":"8e32b17c1422c14cc9e678c7a07c08a6ce9f01da591e6cbda0a932cde3bb35c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hgeni+JftF4mGFez4n4xVYESApU1NqjE8xtdHlAA4gxzC4quw1jpQNjTRKg5BjHox1yTm2LNaJz7uZeTsKKrAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T01:06:25.492969Z","bundle_sha256":"62b6e1096bbbab31d03390096d838af23063d1d3acb0857d66f6cac65822fe1f"}}